初始化项目，由ModelHub XC社区提供模型

Model: apple/SimpleSD-4B-thinking
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

LICENSE

@@ -0,0 +1,88 @@
+Disclaimer: IMPORTANT: This Apple Machine Learning Research Model is
+specifically developed and released by Apple Inc. ("Apple") for the sole purpose
+of scientific research of artificial intelligence and machine-learning
+technology. “Apple Machine Learning Research Model” means the model, including
+but not limited to algorithms, formulas, trained model weights, parameters,
+configurations, checkpoints, and any related materials (including
+documentation).
+
+This Apple Machine Learning Research Model is provided to You by
+Apple in consideration of your agreement to the following terms, and your use,
+modification, creation of Model Derivatives, and or redistribution of the Apple
+Machine Learning Research Model constitutes acceptance of this Agreement. If You
+do not agree with these terms, please do not use, modify, create Model
+Derivatives of, or distribute this Apple Machine Learning Research Model or
+Model Derivatives.
+
+* License Scope: In consideration of your agreement to abide by the following
+  terms, and subject to these terms, Apple hereby grants you a personal,
+  non-exclusive, worldwide, non-transferable, royalty-free, revocable, and
+  limited license, to use, copy, modify, distribute, and create Model
+  Derivatives (defined below) of the Apple Machine Learning Research Model
+  exclusively for Research Purposes. You agree that any Model Derivatives You
+  may create or that may be created for You will be limited to Research Purposes
+  as well. “Research Purposes” means non-commercial scientific research and
+  academic development activities, such as experimentation, analysis, testing
+  conducted by You with the sole intent to advance scientific knowledge and
+  research. “Research Purposes” does not include any commercial exploitation,
+  product development or use in any commercial product or service.
+
+* Distribution of Apple Machine Learning Research Model and Model Derivatives:
+  If you choose to redistribute Apple Machine Learning Research Model or its
+  Model Derivatives, you must provide a copy of this Agreement to such third
+  party, and ensure that the following attribution notice be provided: “Apple
+  Machine Learning Research Model is licensed under the Apple Machine Learning
+  Research Model License Agreement.” Additionally, all Model Derivatives must
+  clearly be identified as such, including disclosure of modifications and
+  changes made to the Apple Machine Learning Research Model. The name,
+  trademarks, service marks or logos of Apple may not be used to endorse or
+  promote Model Derivatives or the relationship between You and Apple. “Model
+  Derivatives” means any models or any other artifacts created by modifications,
+  improvements, adaptations, alterations to the architecture, algorithm or
+  training processes of the Apple Machine Learning Research Model, or by any
+  retraining, fine-tuning of the Apple Machine Learning Research Model.
+
+* No Other License: Except as expressly stated in this notice, no other rights
+  or licenses, express or implied, are granted by Apple herein, including but
+  not limited to any patent, trademark, and similar intellectual property rights
+  worldwide that may be infringed by the Apple Machine Learning Research Model,
+  the Model Derivatives or by other works in which the Apple Machine Learning
+  Research Model may be incorporated.
+
+* Compliance with Laws: Your use of Apple Machine Learning Research Model must
+  be in compliance with all applicable laws and regulations.
+
+* Term and Termination: The term of this Agreement will begin upon your
+  acceptance of this Agreement or use of the Apple Machine Learning Research
+  Model and will continue until terminated in accordance with the following
+  terms. Apple may terminate this Agreement at any time if You are in breach of
+  any term or condition of this Agreement. Upon termination of this Agreement,
+  You must cease to use all Apple Machine Learning Research Models and Model
+  Derivatives and permanently delete any copy thereof. Sections 3, 6 and 7 will
+  survive termination.
+
+* Disclaimer and Limitation of Liability: This Apple Machine Learning Research
+  Model and any outputs generated by the Apple Machine Learning Research Model
+  are provided on an “AS IS” basis. APPLE MAKES NO WARRANTIES, EXPRESS OR
+  IMPLIED, INCLUDING WITHOUT LIMITATION THE IMPLIED WARRANTIES OF
+  NON-INFRINGEMENT, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE,
+  REGARDING THE APPLE MACHINE LEARNING RESEARCH MODEL OR OUTPUTS GENERATED BY
+  THE APPLE MACHINE LEARNING RESEARCH MODEL. You are solely responsible for
+  determining the appropriateness of using or redistributing the Apple Machine
+  Learning Research Model and any outputs of the Apple Machine Learning Research
+  Model and assume any risks associated with Your use of the Apple Machine
+  Learning Research Model and any output and results. IN NO EVENT SHALL APPLE BE
+  LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+  IN ANY WAY OUT OF THE USE, REPRODUCTION, MODIFICATION AND/OR DISTRIBUTION OF
+  THE APPLE MACHINE LEARNING RESEARCH MODEL AND ANY OUTPUTS OF THE APPLE MACHINE
+  LEARNING RESEARCH MODEL, HOWEVER CAUSED AND WHETHER UNDER THEORY OF CONTRACT,
+  TORT (INCLUDING NEGLIGENCE), STRICT LIABILITY OR OTHERWISE, EVEN IF APPLE HAS
+  BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+* Governing Law: This Agreement will be governed by and construed under the laws
+  of the State of California without regard to its choice of law principles. The
+  Convention on Contracts for the International Sale of Goods shall not apply to
+  the Agreement except that the arbitration clause and any arbitration hereunder
+  shall be governed by the Federal Arbitration Act, Chapters 1 and 2. 
+
+Copyright (C) 2026 Apple Inc. All Rights Reserved.

README.md

@@ -0,0 +1,69 @@
+---
+license: apple-amlr
+base_model:
+- Qwen/Qwen3-4B-Thinking-2507
+tags:
+- self-distillation
+- code-generation
+library_name: transformers
+---
+
+# SimpleSD-4B-thinking
+
+This model is an example of the **Simple Self-Distillation (SimpleSD)** method that improves code generation by fine-tuning a language model on its own sampled outputs—without rewards, verifiers, teacher models, or reinforcement learning. Please see the paper below for more information. This uses Qwen for initialization.
+
+- **Self-distillation sampling:** temperature=1.1, top_p=0.95, top_k=20
+- **Evaluation sampling:** temperature=0.7, top_p=0.95, top_k=20
+
+paper: https://arxiv.org/abs/2604.01193
+
+code: https://github.com/apple/ml-ssd
+
+
+## Notes
+- These are research checkpoints for reproducibility.
+- They are not optimized Qwen releases.
+- They don't represent a broader open-source model strategy.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("apple/SimpleSD-4B-thinking")
+tokenizer = AutoTokenizer.from_pretrained("apple/SimpleSD-4B-thinking")
+```
+
+## Method
+
+SimpleSD samples solutions from the base model using non-unit temperature and top-k/top-p truncation, then fine-tunes on those samples via standard supervised learning. Despite its simplicity, SimpleSD yields large gains on competitive programming benchmarks, with improvements concentrating on harder problems. The mechanism traces to resolving a *precision–exploration conflict*: SimpleSD reshapes token distributions in a context-dependent way so that a single global decoding configuration becomes far more effective at evaluation time.
+
+## Results
+
+LiveCodeBench (%)
+
+| Model | LCBv6 pass@1 | LCBv6 pass@5 | LCBv5 pass@1 | LCBv5 pass@5 |
+|---|---|---|---|---|
+| Qwen3-4B-Thinking-2507 (base) | 54.5 | 67.5 | 59.6 | 70.3 |
+| **+ SimpleSD (this model)** | **57.8** (+3.3) | **71.4** (+3.9) | **63.1** (+3.5) | **74.7** (+4.4) |
+
+## Paper
+
+[**Embarrassingly Simple Self-Distillation Improves Code Generation**](https://arxiv.org/abs/2604.01193)
+
+```bibtex
+@misc{zhang2026embarrassinglysimpleselfdistillationimproves,
+      title={Embarrassingly Simple Self-Distillation Improves Code Generation},
+      author={Ruixiang Zhang and Richard He Bai and Huangjie Zheng and Navdeep Jaitly and Ronan Collobert and Yizhe Zhang},
+      year={2026},
+      eprint={2604.01193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2604.01193},
+}
+```
+
+
+## License
+
+This model is released under the [Apple Machine Learning Research Model License](https://huggingface.co/apple/SimpleSD-4B-thinking/blob/main/LICENSE).

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 +1,86 @@
+{%- 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<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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",
+  "trust_remote_code": true
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac93bed40ddc915fdf13e17a500f983d3e5fd1c45961a31b03709a764db03bb
+size 3957900808

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1179ce4abee5d938fbca4a6e67c542b342bab22f59456fdc042123f74da0830c
+size 3987450496

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88ee7e6188fe7bc9ab5b88aecd946bb03033c4861d2471d92bff8994036fce9
+size 99630608

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+    "metadata": {
+        "total_size": 8045591552
+    },
+    "weight_map": {
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.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": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}