Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+context_benchmarks.png filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Glm4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151329,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "model_type": "glm4",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 151343
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91303db34a6d8e7b82912f7dd89cf7ae9a99035758b8532d34840d61c2fb538b
+size 4930586088

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b139c5ca1d95662fcadc39a080a8d527cbf0ebe07b706265685112647113844
+size 4954735776

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8feb1140ca9aa23a5cbce7d1a4f41ef17be54857d131084b79fb93e578e396
+size 4983134872

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c6388f05abc52efbe35eac6e2bb6390c977710d09e2924832bc1a2c0cef66f
+size 4957943672

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7501a4795bc57da1c60deff0e845308c15ab915506a6fe4f8411018b345b03
+size 4951577552

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf45c73223369e4d96908b125abb83b1592f15df7c4cc6313bc1b7634ad7ed1
+size 4882396432

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32572fcfe8bab938df2ff753e82469164bee82b864345acfa6e01c179b5fd207
+size 4951589944

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe83f3b7e3128dc57545721487a09db8809ea242a5885c997fba91da3e14db7f
+size 4498717808

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae352f60a130eae62ab23fd2d61dc5fd1a66900716058296b9a46f003e0de03
+size 4592964328

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c03b933835e2acb380b60e96beaec2a76cc8d3b2f781ef61e7e7c5df31cc9e
+size 4876104776

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3a552fb47e371233e29369b1a73b7db18a11dd6d598e914737e30de25808e5
+size 4879250592

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36fead651ecc9ad1ee1c711a1a6deaa264839cfddd346ba5912821bb55a81dd
+size 4539512216

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e891b65a28a8a0ebf894e80ee7b5e4e89db1ae48a690eccdd42a270e8e7c5c
+size 4961039864

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f618cf00485b326dec9f928b25668ea42a6b3ce95fe0ec723da3adbc4a72d1d
+size 2167544784

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors", "lm_head.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.23.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.41.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.42.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.45.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.49.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.49.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.54.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.58.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.59.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.60.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}