Initial release (#1)

- Initial release (eaa6b9c21fe0e1a07ec3be38f43fb63bdf3ac6d8)


Co-authored-by: LYU,Zongwei <LYUZongwei@users.noreply.huggingface.co>

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1755004394

Modelfile

@@ -0,0 +1,16 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant."""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,151 @@
+---
+license: apache-2.0
+model_type:
+  - reward-model
+domain:
+  - nlp
+language:
+  - en
+  - zh
+metrics:
+  - spearman
+tags:
+  - evaluator
+  - reward-model
+  - rebuttal
+tools:
+  - vllm
+  - openai api
+---
+# Rebuttal-RM 🏅 
+## Introduction 
+Rebuttal-RM is an open-source scorer that emulates human reviewers when judging an author’s reply to a peer-review comment.
+
+#### 1.1 Purpose  
+* Produce four rubric-aligned 0-to-10 scores  
+  1. Attitude (tone & professionalism)  
+  2. Clarity (logical flow)  
+  3. Persuasiveness (strength of evidence)  
+  4. Constructiveness (actionable improvement)  
+* Return a short textual explanation for transparency.  
+* Serve both as (i) a public benchmark and (ii) the reward signal for RebuttalAgent RL.
+
+#### 1.2 Model I/O  
+Input : {relevant paper chunks} + {full review Ri} + {target comment} + {candidate response}
+Output: {
+"score": {Attitude, Clarity, Persuasiveness, Constructiveness},
+"explanation": "..."
+}
+
+#### 1.3 Model Recipe  
+* Backbone: **Qwen-3-8B-Chat**  
+* Supervised fine-tuning on the RM_Bench dataset  
+ 
+
+The resulting model offers reproducible, high-fidelity evaluation 
+
+---
+
+## 2 Performance (agreement with human ratings)
+
+### Table – Consistency between automatic scores and human ratings  
+*Higher values indicate better agreement.*
+### Consistency between automatic scores and human ratings (higher = better)
+| Scoring Model | Attitude r | Attitude β | Attitude f | Clarity r | Clarity β | Clarity f | Persuasiveness r | Persuasiveness β | Persuasiveness f | Constructiveness r | Constructiveness β | Constructiveness f | Avg |
+|-------------- |:---------:|:----------:|:----------:|:---------:|:----------:|:----------:|:-----------------:|:----------------:|:----------------:|:-------------------:|:-------------------:|:------------------:|:---:|
+| Qwen-3-8B      | 0.718 | 0.672 | 0.620 | 0.609 | 0.568 | 0.710 | 0.622 | 0.577 | 0.690 | 0.718 | 0.745 | 0.720 | 0.664 |
+| Llama-3-8B     | 0.297 | 0.347 | 0.540 | 0.158 | 0.047 | 0.380 | 0.272 | 0.245 | 0.560 | 0.424 | 0.457 | 0.460 | 0.349 |
+| GLM-4-9B       | 0.420 | 0.475 | 0.460 | 0.467 | 0.436 | 0.730 | 0.369 | 0.361 | 0.700 | 0.561 | 0.519 | 0.570 | 0.506 |
+| GPT-4.1        | 0.743 | 0.712 | 0.800 | 0.739 | 0.671 | 0.750 | 0.779 | 0.763 | 0.740 | 0.804 | 0.756 | 0.680 | 0.745 |
+| DeepSeek-R1    | 0.646 | 0.633 | 0.790 | 0.708 | 0.615 | 0.760 | 0.710 | 0.664 | 0.720 | 0.742 | 0.701 | 0.620 | 0.705 |
+| DeepSeek-V3    | 0.699 | 0.733 | 0.710 | 0.687 | 0.578 | 0.740 | 0.697 | 0.652 | 0.770 | 0.771 | 0.719 | 0.750 | 0.692 |
+| Gemini-2.5     | 0.620 | 0.509 | 0.750 | 0.605 | 0.593 | 0.540 | 0.627 | 0.607 | 0.520 | 0.711 | 0.705 | 0.610 | 0.616 |
+| Claude-3.5     | 0.569 | 0.635 | 0.720 | 0.704 | 0.670 | 0.680 | 0.706 | 0.686 | 0.670 | 0.753 | 0.738 | 0.630 | 0.680 |
+| **Rebuttal-RM**| **0.839** | **0.828** | **0.910** | **0.753** | **0.677** | **0.790** | **0.821** | **0.801** | **0.820** | **0.839** | **0.835** | **0.810** | **0.812** |
+
+
+## 3 Deployment / Usage
+
+
+### 3.1 Run with vLLM (OpenAI protocol)
+```bash
+pip install "vllm>=0.4.2"
+python -m vllm.entrypoints.openai.api_server \
+  --model Zhitao-He/Rebuttal-RM \
+  --dtype auto \
+  --port 8000
+```
+### 3.2 Query via the official openai SDK
+```
+python
+
+import openai
+openai.api_key  = "EMPTY"
+openai.base_url = "http://localhost:8000/v1"
+
+prompt = f"""
+The whole review content is{Full_Review_Content}
+The target comment content is{Target_Comment}.
+The best relevant paper fragment is{Relevant_Paper_Fragment}.
+The response is{response}
+"""
+
+resp = openai.chat.completions.create(
+    model="Zhitao-He/Rebuttal-RM",
+    messages=[
+        {"role": "system", "content": system_prompt}, 
+        {"role": "user",   "content": user_prompt}
+    ],
+    temperature=0.7
+)
+print(resp.choices[0].message.content）
+
+```
+### 3.3 Default System Prompt (system_prompt)
+```
+You are a seasoned academic reviewer and response optimization expert. Your task is to evaluate the quality of the response based on the review comments, paper fragments, and the authors' responses. Please strictly follow the requirements below, and output only the score and score explanation.
+
+Input variables:
+
+review_content: Complete content of the review comments. similar_paper_fragments: Best paper fragment most relevant to the comment. comment: Specific segment of the review comments. original_response: The authors' original response text to the comment.
+
+Your task: Based on the input information, output only a JSON object containing the following two items:
+Scoring Standard
+Score Range: 0 - 10
+0: Wholly Ineffective
+1-2: Perfunctory
+3-4: Unconvincing
+5-6: Addresses Some Concerns
+7-8: Exceptional
+9-10: Outstanding
+score: Four-dimensional score breakdown, ranging from 0-10, structured as follows:
+Attitude: The tone and professionalism of the response. 
+Clarity: The logic, structure, and focus of the response.
+Persuasiveness: The effectiveness of the argumentation and evidence support. 
+Constructiveness: The commitment to revisions and specific actions taken.
+
+score_explanation: A brief explanation of each score, specifically citing key points from the response text that reflect the scores and any shortcomings.
+
+Output requirements:
+
+Only output the JSON object; do not include any other characters or explanations.
+The scoring must be reasonable, and the score explanation must clearly reference the original text that reflects the score. 
+All output must be in formal, polite academic English.
+Your output must be strictly JSON formal which can be dirctly loaded by json.load()
+Output format example:
+{ "score": { "Attitude": <int>,
+              "Clarity": <int>, 
+              "Persuasiveness": <int>,
+              "Constructiveness": <int> }, 
+  "score_explanation": <explanation for your given score>}"""
+```
+## 4 Citation
+```
+@inproceedings{he2025rebuttalagent,
+  title     = {RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind},
+  author    = {Zhitao He and Zongwei Lyu and Wuzhenhai Dai and Yi R. (May) Fung},
+  year      = {2025},
+  institution = {Hong Kong University of Science and Technology},
+  url       = {https://arxiv.org/abs/YYMM.NNNNN}
+}
+```

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 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "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": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "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": "4.52.4"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92467eb87fa7aa92e5da707b66d4a15eb4189d3acb59b73f5d0acf041e8c7018
+size 2489319560

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e072b5926f56fd3efd175e3c544289a96af84004950d5268e675d98fdfd84c
+size 1912674536

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54401f2a6ed37ea3c7801d593d328d48b365ed6cf24e713cf4110b932415d7e8
+size 1946260384

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33326c3215601757626044eac47c26a6b56273c83ae79390bf4627eb753b9d7c
+size 1912674536

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb68c52e41ea893780a1d0fda5489aec0cbf701a7db420be76115dd79eca0e7
+size 1946260384

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105fab3337b8f420333fc2048741d6871cb327bb86ab4f72a4c275309b78f8da
+size 1912674568

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c647353b46c5a8fa87d8f34a01d5099b9e136828a03dddd5a36c60f4ff50b0
+size 1946260408

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4cb4e6de28108c2ddd4b52f317d00b8b6cd7bdd0be64d8c240f97ce9c2869e
+size 1912674568

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da47e1797f54d3c18deb60d3d4089cfcb0278341c12947ad5c71d5e28b7e07a
+size 1946260408

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0c9098771b2c84db88c2522225884b5331fcfbf9876f7d7c5498361bc2e6d6
+size 1912674568

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954408eccf7a2ee12d59e13dbc937358b329889acef4ca302526fb5896ec7de4
+size 1946260408

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:365128243a8ff9d04c2d04f31095a5578d76faff299590daf57275ddcc819085
+size 1912674568

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97caa64db297317dc428b3ecaf1a1b2c67ae2a2fdf0b4102f4c9e57cba212e7f
+size 1946260408

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863b5b3656d35f2dff155b5c79fa449a011610852a352c92b7c9eca8fdbe4042
+size 1912674568

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb1ba0fbfb7628f33f0bbde4270ef93540ffaf4d781c125360286c7f0e95372
+size 1946260408

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9108ac78362e4b2f53ec98ed190a2f03d618e11ec60257528131c0a5df5be465
+size 2489319552

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ba4c0d8fea695359ef6df9013a6b01245d8110054dcf9f3cde355eab32f457
+size 771803472

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 32762941440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00016-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}