Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ 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

README.md

@@ -1,3 +1,36 @@
 ---
-license: apache-2.0
+license: mit
+library_name: mlx
+tags:
+- mlx
+pipeline_tag: text-generation
+base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
 ---
+
+# mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ
+
+This model [mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ](https://huggingface.co/mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ) was
+converted to MLX format from [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
+using mlx-lm version **0.24.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,1236 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "model.embed_tokens": {
+            "group_size": 32,
+            "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": 4
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.0.self_attn.q_norm": false,
+        "model.layers.0.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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": 4
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.1.self_attn.q_norm": false,
+        "model.layers.1.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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": 4
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.2.self_attn.q_norm": false,
+        "model.layers.2.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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": 4
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.3.self_attn.q_norm": false,
+        "model.layers.3.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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": 4
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.4.self_attn.q_norm": false,
+        "model.layers.4.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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": 4
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.5.self_attn.q_norm": false,
+        "model.layers.5.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.6.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.7.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.8.self_attn.q_norm": false,
+        "model.layers.8.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.9.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.10.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.11.self_attn.q_norm": false,
+        "model.layers.11.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.12.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.13.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.14.self_attn.q_norm": false,
+        "model.layers.14.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.15.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.16.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.17.self_attn.q_norm": false,
+        "model.layers.17.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.18.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.19.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.20.self_attn.q_norm": false,
+        "model.layers.20.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.21.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.22.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.23.self_attn.q_norm": false,
+        "model.layers.23.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.24.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.25.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.26.self_attn.q_norm": false,
+        "model.layers.26.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.27.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.28.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.29.self_attn.q_norm": false,
+        "model.layers.29.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.30.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.31.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.32.self_attn.q_norm": false,
+        "model.layers.32.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.q_norm": false,
+        "model.layers.33.self_attn.k_norm": false,
+        "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.q_norm": false,
+        "model.layers.34.self_attn.k_norm": false,
+        "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": 4
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.layers.35.self_attn.q_norm": false,
+        "model.layers.35.self_attn.k_norm": false,
+        "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": 4
+        },
+        "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.norm": false,
+        "lm_head": {
+            "group_size": 32,
+            "bits": 4
+        }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "rope_type": "yarn",
+        "factor": 4.0,
+        "original_max_position_embeddings": 32768,
+        "attn_factor": 0.8782488562869419
+    },
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.0",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e3b583241de5a9c6ca377239fa56415f42c5338db8bd0016ecce1f84f4d809
+size 4685626408

model.safetensors.index.json

@@ -0,0 +1,914 @@
+{
+    "metadata": {
+        "total_size": 4685522944
+    },
+    "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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.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_norm.weight": "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_norm.weight": "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.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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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"
+    }
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d5fd6d2f8cf1172ac86cf982e2b88fa6732366b44dc1a32349379a54a6a044
+size 11423346

tokenizer_config.json

@@ -0,0 +1,243 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151670": {
+      "content": "<｜Assistant｜>",
+      "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='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- 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｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}