初始化项目，由ModelHub XC社区提供模型

Model: FreedomIntelligence/HuatuoGPT-3-32B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+language:
+- en
+- zh
+base_model:
+- Qwen/Qwen3-32B
+tags:
+- medical
+- reasoning
+---
+
+<div align="center">
+  <h1>🩺 HuatuoGPT-3-32B</h1>
+</div>
+
+<div align="center">
+  <a href="https://github.com/FreedomIntelligence/HuatuoGPT-3" target="_blank">🏠 GitHub</a>
+  |
+  <a href="" target="_blank">📄 Paper</a>
+</div>
+
+# <span>Introduction</span>
+
+**HuatuoGPT-3** is an open-source medical LLM trained with **SeedRL**, an RL-only domain adaptation paradigm that transforms a base model into a medical expert in a single RL stage.
+
+For more information, visit our GitHub repository:
+[https://github.com/FreedomIntelligence/HuatuoGPT-3](https://github.com/FreedomIntelligence/HuatuoGPT-3)
+
+> [!IMPORTANT]
+> **HuatuoGPT-3-32B is set to thinking mode by default.** The output contains a `<think>...</think>` reasoning block followed by the final response after `</think>`. 
+
+# <span>Model Info</span>
+
+| Model | Description | Backbone | Link |
+| --- | --- | --- | --- |
+| **HuatuoGPT-3-32B** | 32B medical LLM trained with SeedRL | Qwen3-32B | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-32B) |
+| **HuatuoGPT-3-8B** | 8B medical LLM trained with SeedRL | Qwen3-8B-Base | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-8B) |
+| **HuatuoGPT-3-7B-Pangu** | 7B medical LLM trained with SeedRL | openPangu-Embedded-7B | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-7B-Pangu) |
+
+
+# <span>Usage</span>
+
+You can use HuatuoGPT-3-8B in the same way as `Qwen3-32B`. You can deploy it with tools like [vLLM](https://github.com/vllm-project/vllm) or [SGLang](https://github.com/sgl-project/sglang), or perform direct inference:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "FreedomIntelligence/HuatuoGPT-3-32B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+messages = [
+    {"role": "user", "content": "A patient has fever, cough, and shortness of breath. What should be considered first?"}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=4096)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+# <span>📖 Citation</span>
+
+```bibtex
+@inproceedings{huatuogpt3,
+  title={OnePO: Direct One-stage Policy Optimization for SFT-free Domain Adaptation},
+  author={Chen, Junying and Xie, Xinyuan and Li, Ziniu and Wang, Benyou},
+  booktitle={Proceedings of the 43rd International Conference on Machine Learning},
+  series={Proceedings of Machine Learning Research},
+  volume={306},
+  year={2026}
+}
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b305c7ff9f2bb45efd59f58e12540510e921471600599e4c424f57fbd0e23c3b
+size 4771120312

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e338c3ac0ab2f1213a21badbab382630b4d771ae2c431acf14a000ce87ccd957
+size 4844519904

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85da6dcd660dbb117b796c32b46b411227a2eb1425f8249c02120cc3eb7ad6c0
+size 4858928400

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d18bbbebf1695de14db4760618246a913ee5742356ef4e79afbd3db63dce7313
+size 4739717832

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858c1069ffd81aa15cd939f2654f8a5ed43ba8a6c26e4811b48779875a41673c
+size 4865492768

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2e6f5d1486efeec8ef00caf541d620f14c9b4d2ccd1a21bc49fe3eb8172710
+size 3449872816

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6796413b6a393b8e6040be61f82ef2dcf2477664179598517bac33132d15ab55
+size 4827417472

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5fe31e6054cf76c5e03081f27ebb8b2a1e32aadde50715fdc629e2f22a61a9
+size 4991354656

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f12767e233207d1e5dd0c290a44046b5fcec52c43d9c7feabd65f5aa4e5df3
+size 4750189592

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e4b78030f359623b505c173b15d7f483c43e7494fbc9c12830720297815db4
+size 4813044240

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba54a9fdc0f1d2bd68d4c934ad50ec3c801d3c95642b9f36620306af53251f01
+size 4938915648

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a382badeb9fde0bc622aa8d6031f141ec63b0144284a32f75b35fa9fe3a0fbd
+size 4970361080

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced63af89138398ce956176beaff025d61dbb2d6da45d683630881b41aec0c9d
+size 4959887008

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab84a641aa87817e78db34a1c1fbff28e32e07dc091c5eb65bec9e2c488a7a3
+size 3743506696

model.safetensors.index.json

@@ -0,0 +1,715 @@
+{
+  "metadata": {
+    "total_parameters": 32762123264,
+    "total_size": 65524246528
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.norm.weight": "model-00007-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "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": "<|im_end|>",
+      "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}