diff --git a/.gitattributes b/.gitattributes
index 551fa4166315ed87a4d932bf8465ff8e333bce1a..75382f2fa883c4b4046312522d5dfbea76c904c7 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -42,3 +42,14 @@ DeepSeek-R1-Distill-Qwen-14B_3bit/tokenizer.json filter=lfs diff=lfs merge=lfs -
DeepSeek-R1-Distill-Qwen-14B_2,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-14B_3,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-14B_6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e9831983e3e28eef64615b2fa639243dbda60ab6
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/config.json
@@ -0,0 +1,3029 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/model.safetensors b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..312ce9c50a6ff193356cbda5fcd88a9baf04751b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8726362ae8224aeb9f3a381f02178df6a572c720ad9ab7ce890e40b19aea314d
+size 5267968765
diff --git a/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..40337556eb14c66c098e2763fd9fe1f4b9186dbc
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 5267826688
+ },
+ "weight_map": {
+ "lm_head.biases": "model.safetensors",
+ "lm_head.scales": "model.safetensors",
+ "lm_head.weight": "model.safetensors",
+ "model.embed_tokens.biases": "model.safetensors",
+ "model.embed_tokens.scales": "model.safetensors",
+ "model.embed_tokens.weight": "model.safetensors",
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.32.input_layernorm.weight": "model.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.33.input_layernorm.weight": "model.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.34.input_layernorm.weight": "model.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.35.input_layernorm.weight": "model.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.36.input_layernorm.weight": "model.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.37.input_layernorm.weight": "model.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.38.input_layernorm.weight": "model.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.39.input_layernorm.weight": "model.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.40.input_layernorm.weight": "model.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.41.input_layernorm.weight": "model.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.42.input_layernorm.weight": "model.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.43.input_layernorm.weight": "model.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.44.input_layernorm.weight": "model.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.45.input_layernorm.weight": "model.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.46.input_layernorm.weight": "model.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.47.input_layernorm.weight": "model.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+ "model.norm.weight": "model.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-2,6_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/config.json b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c666d679ba14c74ddbb4b359e3f39bb19a44c5e8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/config.json
@@ -0,0 +1,3029 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model-00001-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4331a3a393861c10484b4bf8f4859f9fd59a8a17
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdd1c75fe542d1c9b5ded243fd1ae6c627c852e07f466d67181991d448555ea
+size 5348117358
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model-00002-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..13d910198e7385862eec9e58a46099ea4004080e
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744229f4c2a22a1301aa5a3d582efa7ba228c9b460eaf47b2dd85b8e7a57fb24
+size 1440613893
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..f1879fb354a8c0025f91d3f91d129b0ccdcdb1c9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 6788589568
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00002-of-00002.safetensors",
+ "lm_head.scales": "model-00002-of-00002.safetensors",
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,4_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c666d679ba14c74ddbb4b359e3f39bb19a44c5e8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/config.json
@@ -0,0 +1,3029 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model-00001-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4331a3a393861c10484b4bf8f4859f9fd59a8a17
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdd1c75fe542d1c9b5ded243fd1ae6c627c852e07f466d67181991d448555ea
+size 5348117358
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model-00002-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..13d910198e7385862eec9e58a46099ea4004080e
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744229f4c2a22a1301aa5a3d582efa7ba228c9b460eaf47b2dd85b8e7a57fb24
+size 1440613893
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..f1879fb354a8c0025f91d3f91d129b0ccdcdb1c9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 6788589568
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00002-of-00002.safetensors",
+ "lm_head.scales": "model-00002-of-00002.safetensors",
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3,6_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/config.json b/DeepSeek-R1-Distill-Qwen-14B-3bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..502999a475cee55cfd57d529a6eb218d1e3f659b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/model-00001-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-3bit/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7d6139719f7beaa8fc61d828c27045905c3c9c6
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9688fa20775d61c528a48a239a4a57e58547c5a4f577273a5bf4ec00ad971bf9
+size 5366751564
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/model-00002-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-3bit/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b610c9a1c0feb86649b10b633a0dd15b9ae8a7fe
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7dc1b46731e6536b10a3b39388101040e4b0c76235aef48a9c6110c698fbcf
+size 1096593521
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-3bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..f15e55d90823dafd7075dfcba8e30ac53d760032
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 6463203328
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00002-of-00002.safetensors",
+ "lm_head.scales": "model-00002-of-00002.safetensors",
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-3bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-3bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfee778060553575b8a82ede5a22863c924ab4b2
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/config.json
@@ -0,0 +1,3029 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 6
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 6
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model-00001-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4df2a5a3a11a4b7e16da2d938f7669771d4c368d
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c71c01a2c8003f356e45fd63b08b78c2d28102aa026bcdea361ee6109338c7c
+size 5367725398
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model-00002-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77e5b4b661a346bf68961ea9892b40e7a614058d
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d24884c671d51068e3d9c245cabadf0bf8970d99d3a11d1da5227a5b87da7ef
+size 3592541399
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..97f3c4a0cd41e351b6472cb684781afe928526a8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 8960124928
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00002-of-00002.safetensors",
+ "lm_head.scales": "model-00002-of-00002.safetensors",
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,6_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/config.json b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e12928c3bcee5ad84e60082d9431ef21d4b716a
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/config.json
@@ -0,0 +1,3029 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 8
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 8
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model-00001-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..973072bd52730a122a94d01a75f99e2e91dd176b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27108a8c6ada421df46a5f048996f810e852e6bd98b946592b923725b18a1b9
+size 5343568565
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model-00002-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fc98d952ce78b5b9314e51dd2b83cca95f908ba8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bd582135369ce6d1bd6d3ad9d1c11cab93ea4574fb16a00f42cf9b1b597ecc
+size 4267470721
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..2135b88b0c71c66cf9f6db6e5c1eff4aac99eefa
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 9610897408
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00002-of-00002.safetensors",
+ "lm_head.scales": "model-00002-of-00002.safetensors",
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4,8_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/config.json b/DeepSeek-R1-Distill-Qwen-14B-4bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c72c7702157d4588fb410677d9c819cdda200d9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/model-00001-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-4bit/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..eb90bfb2dba5d0775797b57910394c1da6d13f7e
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561eacdd7d4d652063a099fb0b6b5340f9e3f82263f7dca70fcf9e026f5860e9
+size 5353840339
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/model-00002-of-00002.safetensors b/DeepSeek-R1-Distill-Qwen-14B-4bit/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ce5df2e9b1c19fa12eb956c320dd4d32b4be5806
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ec75fe3ad8aa351fce70d1184625b275d4ba578212951e8e4f1883fcc92ed3
+size 2955654022
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-4bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..7b762296a5ee48da56f5585b9c0e23ecf5c42cb8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 8309352448
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00002-of-00002.safetensors",
+ "lm_head.scales": "model-00002-of-00002.safetensors",
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-4bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-4bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/config.json b/DeepSeek-R1-Distill-Qwen-14B-6bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a3a29ddadfadd0d79286e6885f1d519d50c808f0
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00001-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c4a9c652d5295b88d25577b028093db69f12add0
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b9dc7b7458181c1b00cacad6a81baa4b5fb79cc30bcd19fd7dd4edd9804642
+size 5359687445
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00002-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..aed472fb57ccc9d6e624cb93b054ca16ebd0501a
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d839932beb2a5bd6c66944983b96526e995349c963ff83b376098f5b4d009149
+size 5368304692
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00003-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e6ba5aa9f0bdaa856495e2c6145498e84ce59996
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093c82ec757774968362248c9545787d96695e42371858d31b99caccc9f47940
+size 1273800278
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-6bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..1029aa0a08e5b33b73e1bcb9ed37fb5b353644dd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 12001650688
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00003-of-00003.safetensors",
+ "lm_head.scales": "model-00003-of-00003.safetensors",
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-6bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-6bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/config.json b/DeepSeek-R1-Distill-Qwen-14B-8bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..387c6b17ef61be1cdac6705e787925b37787492c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00001-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b0124f1112d0e0a1cd998b4b0ef6edd106e47117
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4840d14f443ab6ec2601cc20b38ceeade1a58d149326c2cd74fe6d1115417f5
+size 5356676399
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00002-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..289c943899efa7f680b707eaa38a785badfbd00d
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a7cbd1153728d504df25702063be6d4346edf4dbfc37da40fe4cfbfae4c70b
+size 5340062024
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00003-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c3895be6e8d1d3b2d7688ff7bcefbb6cea4fea83
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea82122de176b34c561feb52bd87c51119ad132b643e4832f4c69223696bfee
+size 4997352900
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-8bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..37251537435e664858b659b12b374dec936920f2
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/model.safetensors.index.json
@@ -0,0 +1,1262 @@
+{
+ "metadata": {
+ "total_size": 15693948928
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00003-of-00003.safetensors",
+ "lm_head.scales": "model-00003-of-00003.safetensors",
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-8bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-8bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/config.json b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2290c506c11453e5b5f8b3024e8ba387698c46bb
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/config.json
@@ -0,0 +1,27 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00001-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00001-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a953715deb2cefc4a779b2ab5245affeceeec94
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00001-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937f5c8854aef5e4b096a7f40e3eacc2b5b8b43c987368003e1cf855b3454bb1
+size 5269326976
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00002-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00002-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a0602e6c1ae6e6c242ed1cf8fb6a208bf8129308
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00002-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee7d19840f7f60587377c20bb1569d4c9699b8a4d159661d042a047856f3918
+size 5363828073
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00003-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00003-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..50f02cd2783857367d7f563d96820a1f1e59ea30
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00003-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1494d062a3268b72295943568de92ba43d7a0bb1cede4f9c83ed6e8f5e64225d
+size 5363828102
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00004-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00004-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d1a92cc3ea6ac9cacd6bad1564c2ebc5adb0a122
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00004-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d151b24e03942952d7939b929a17b1e8b8eb07e0086fd81373fedf1b10bd23f
+size 5237963142
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00005-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00005-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..62d7aadddf3cad0f1520080cb2fd4fda9e1a2152
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00005-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c776dd494322939c64c75b9ee8e093fe831e9ba7980b44a6e6f4baaf3db01faa
+size 5363828102
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00006-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00006-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bee7f129b699bc17ffe738bed627a66e9ecdc680
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model-00006-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1344b5b2c2b11686b9a055ec8042c4ac3ccf7fbdb7ea30ce266977d272f881
+size 2941359481
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..9beb0226d38be73efab6813bfe3a52f4ba267bb9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/model.safetensors.index.json
@@ -0,0 +1,586 @@
+{
+ "metadata": {
+ "total_size": 29540067328
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00006-of-00006.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.norm.weight": "model-00006-of-00006.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-bfloat16/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/config.json b/DeepSeek-R1-Distill-Qwen-14B-float16/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2290c506c11453e5b5f8b3024e8ba387698c46bb
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/config.json
@@ -0,0 +1,27 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13824,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 48,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model-00001-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00001-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..45ce49d10331e05c161e53ab1eb57414d1818cb3
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00001-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69132aadd1204d2a91f6b5ce9cb940c81cbe170671b83447b87f014ca5790ff5
+size 5269326894
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model-00002-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00002-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b42ce507ff13f4c3410ead974749fa85afac0c62
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00002-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568e1d9b8d91214bbe41f54b2e55002f7aac0bc1dec153c8edadea1ece6c4d80
+size 5363827954
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model-00003-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00003-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9880de8b440fba8006de0575839459054e34a094
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00003-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d9d8877651d2d24c7cceef597eb5b1b05306f6254b780fcc4f88aca3375bef
+size 5363827983
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model-00004-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00004-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b90cb72a6b266a79c8c756a5243937185b778b39
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00004-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26297e52852364d3f165139c35584790e1081f38486e5d2497187307298ab40d
+size 5237963032
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model-00005-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00005-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cbc6be92590f7e831471d8edc3eadfb116ef6183
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00005-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858df989197b8f85346cccb8c9d2775ca1a3b74cb08e4072b925a2930803826a
+size 5363827983
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model-00006-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00006-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..85961daa661ab523f7b4bd28d949f393da557efd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model-00006-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ed2a7966cacdddeadb20cf4840573585782b93d430fe3ec914cb9853241388
+size 2941359451
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-14B-float16/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..9beb0226d38be73efab6813bfe3a52f4ba267bb9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/model.safetensors.index.json
@@ -0,0 +1,586 @@
+{
+ "metadata": {
+ "total_size": 29540067328
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00006-of-00006.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.norm.weight": "model-00006-of-00006.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-14B-float16/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-14B-float16/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/README.md b/README.md
index 0c0ea5714611eb6598cfd87755eaac3e871db57d..687be845a02814b3802ed25aeb5a84afadc7b5a7 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,6 @@
---
quantized_by: sealad886
-license_link: >-
- https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE
+license_link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
@@ -9,7 +8,7 @@ base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
tags:
- chat
- mlx
-license: mit
+- conversations
---
# mlx-community/DeepSeek-R1-Distill-Qwen-14B