commit b32852000c40425f31d9bf3b2290e8df381b4f0f
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Mon Sep 7 16:28:13 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: ScienceOne-AI/S1-DeepResearch-8B-Preview
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..c0bec58
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+ 
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb 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
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model-0003-others-save_rank0.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-0004-others-save_rank0.safetensors filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text
+model-0002-others-save_rank0.safetensors filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text
+model-0001-others-save_rank0.safetensors filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..35452a7
--- /dev/null
+++ b/README.md
@@ -0,0 +1,147 @@
+---
+language:
+- zh
+- en
+license: apache-2.0
+tags:
+- agent
+- deep-research
+- tool-calling
+- long-context
+- reasoning
+pipeline_tag: text-generation
+---
+
+# S1-DeepResearch-8B-Preview
+
+<div align="center">
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/ScienceOne-AI/S1-DeepResearch)
+
+**面向长程深度研究任务的高效能智能体 | High-Performance Deep Research Agent**
+
+[🤗 Model](https://huggingface.co/ScienceOne-AI/S1-DeepResearch-8B-Preview) | [🤖 ModelScope](https://modelscope.cn/models/ScienceOne-AI/S1-DeepResearch-8B-Preview) | [📖 GitHub](https://github.com/ScienceOne-AI/S1-DeepResearch) | [📄 Technical Report (Coming Soon)]()
+
+</div>
+
+---
+
+## 📝 模型简介 | Model Overview
+
+**S1-DeepResearch-8B-Preview** 是由 ScienceOne 团队开发的专门为 **长程深度研究(Deep Research)** 任务设计的开源智能体模型。它可以处理非常复杂的、需要多步推理的信息搜寻任务，并具备强大的连续多轮工具调用能力,能够像人类研究员一样,在海量信息中抽丝剥茧,进行深度的信息检索、阅读、理解与整合。
+
+**S1-DeepResearch is an open-source agent model specifically developed for long-horizon deep research tasks.** it can handle highly complex, multi-step reasoning information retrieval tasks with powerful continuous multi-turn tool calling capabilities, working like a human researcher to perform deep information retrieval, reading, comprehension, and integration.
+
+---
+
+## ✨ 核心特性 | Key Features
+
+- **⚡ 小而不凡 | Small Yet Powerful**
+  - 仅 **8B** 参数量级,保持高推理速度与低部署成本
+  - 在 Agent 任务中表现出优异的主动规划、信息整合能力
+  - Maintains high inference speed and low deployment cost at 8B parameter scale
+  - Exhibits excellent proactive planning and information integration capabilities
+
+- **🏆 性能卓越 | Outstanding Performance**
+  - 在 GAIA、DeepSearch、Browsecomp 等主流深度研究类基准上表现突出
+  - 达到同尺寸模型的 SOTA 水平,并超越一些更大参数量的模型
+  - Achieves SOTA level among same-sized models on mainstream benchmarks
+  - Surpasses some larger parameter models
+
+- **🔄 长链执行 | Long-Chain Execution**
+  - 支持 **128k** 上下文窗口
+  - 能够稳定执行 **100+ 轮**的连续工具调用
+  - 在长链路深度研究推理中保持高度的推理韧性
+  - 128k context length
+  - Capable of stably executing 100+ rounds of continuous tool calls
+
+- **⚙️ 高质量合成数据 | High-Quality Synthetic Data**
+  - 创新的全自动数据合成流水线
+  - 采用搜索-浏览-模糊的合成流程
+  - 知识图谱随机游走策略,自动生成高复杂度、强搜索依赖的问答对数据
+  - Innovative fully automated data synthesis pipeline
+
+---
+
+## 📊 性能评估 | Evaluation
+
+我们在多个权威智能体能力基准上对 S1-DeepResearch 进行了评估。结果表明，S1-DeepResearch 在同参数规模模型中达到领先水平，并在多项任务上凭借高效的推理与规划机制，超越了部分参数规模更大的开源模型。进一步地，在与闭源顶尖模型及专业 Deep Research 系统的对比中，S1-DeepResearch 依然展现出稳定且具竞争力的性能表现。整体结果表明，在合理的智能体架构与推理策略支持下，轻量化但具备高能力密度的模型同样能够有效应对复杂深度研究任务，为深度研究智能体的实际应用提供了一条可行路径。
+
+We evaluate **S1-DeepResearch** across multiple authoritative agent benchmarks. The results show that S1-DeepResearch achieves state-of-the-art performance among models of comparable size, and in several tasks surpasses larger open-source models due to its efficient reasoning and planning mechanisms. Moreover, when compared with leading closed-source models and specialized Deep Research systems, S1-DeepResearch demonstrates consistently competitive performance. These results indicate that **lightweight models with high capability density**, when equipped with well-designed agent architectures and reasoning strategies, can effectively handle complex deep research tasks, offering a practical and scalable solution for real-world research-oriented agent systems.
+
+<div align="center">
+  <img src="https://github.com/ScienceOne-AI/S1-DeepResearch/raw/main/assets/benchmark.png" width="80%" alt="Benchmark Results">
+</div>
+
+### 推理时扩展 | Test-Time Scaling
+
+我们进一步分析了模型在推理时扩展下的性能表现。评测结果显示，S1-DeepResearch 在 Pass@1 到 Pass@3 设置下取得了稳定且显著的性能提升，表明其推理与规划过程在单次推理条件下尚未饱和。该结果说明，通过推理时扩展，模型能够探索更丰富的推理与规划路径，从而有效提升复杂任务的整体成功率。
+
+We further analyze the model’s test-time scaling behavior. S1-DeepResearch shows consistent and significant performance gains from Pass@1 to Pass@3, indicating that its reasoning and planning processes are not saturated under single-sample test. This suggests that test-time expansion enables the model to explore diverse reasoning and planning trajectories, thereby substantially improving task success rates.
+
+<div align="center">
+  <img src="https://github.com/ScienceOne-AI/S1-DeepResearch/raw/main/assets/pass1to3.png" width="80%" alt="Pass@1 to Pass@3 Results">
+</div>
+
+---
+
+
+
+## 🛠️ 使用方式 | Usage
+
+详细的使用说明和示例代码请参考我们的 GitHub 仓库
+
+**For detailed usage instructions and example code, please refer to our GitHub repository:**
+
+👉 **[https://github.com/ScienceOne-AI/S1-DeepResearch](https://github.com/ScienceOne-AI/S1-DeepResearch)**
+
+
+
+---
+
+
+---
+
+## 📜 协议与引用 | License & Citation
+
+### License
+
+本模型采用 **Apache License 2.0** 开源协议。
+
+This model is licensed under **Apache License 2.0**.
+
+### 📑 Citation
+
+
+```bibtex
+@software{s1agent2025,
+    title={S1-DeepResearch: High-Performance Deep Research Agent},
+    author={ScienceOne Team},
+    year={2025},
+    url={https://github.com/ScienceOne-AI/S1-DeepResearch},
+}
+```
+
+---
+
+## 🤝 联系我们 | Contact
+
+- **GitHub Issues**: [https://github.com/ScienceOne-AI/S1-DeepResearch/issues](https://github.com/ScienceOne-AI/S1-DeepResearch/issues)
+
+---
+
+## ⚠️ 免责声明 | Disclaimer
+
+本模型为研究预览版本,可能存在局限性。在生产环境使用前请充分测试。模型输出结果仅供参考,不构成专业建议。
+
+**This model is a research preview and may have limitations. Please test thoroughly before production use. Model outputs are for reference only and do not constitute professional advice.**
+
+---
+
+<div align="center">
+
+**Made with ❤️ by ScienceOne Team**
+
+</div>
+
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..b54f913
--- /dev/null
+++ b/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
+}
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..699ff8d
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..8f8909f
--- /dev/null
+++ b/config.json
@@ -0,0 +1,69 @@
+{
+  "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": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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": 131072,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..3fc809d
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"other"}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..20a8a91
--- /dev/null
+++ b/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": "4.51.0"
+}
\ No newline at end of file
diff --git a/merges.txt b/merges.txt
new file mode 100644
index 0000000..80c1a19
--- /dev/null
+++ b/merges.txt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853
diff --git a/model-0001-others-save_rank0.safetensors b/model-0001-others-save_rank0.safetensors
new file mode 100644
index 0000000..6ced5c6
--- /dev/null
+++ b/model-0001-others-save_rank0.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5871eea0a6ae87cc5891393285b17a3fbfac5893b58e11b8122153a1fb78751
+size 4231141088
diff --git a/model-0002-others-save_rank0.safetensors b/model-0002-others-save_rank0.safetensors
new file mode 100644
index 0000000..b55a9b5
--- /dev/null
+++ b/model-0002-others-save_rank0.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d83edc02ad74befe5274959197d37464133b15838a07a919e444f92e4e7e663
+size 4387458752
diff --git a/model-0003-others-save_rank0.safetensors b/model-0003-others-save_rank0.safetensors
new file mode 100644
index 0000000..2f1b65e
--- /dev/null
+++ b/model-0003-others-save_rank0.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8566c0e7731ca347228a02df03774f9169eb1c3cb226ba718568fd3c546ec4b
+size 4286779488
diff --git a/model-0004-others-save_rank0.safetensors b/model-0004-others-save_rank0.safetensors
new file mode 100644
index 0000000..9fcf087
--- /dev/null
+++ b/model-0004-others-save_rank0.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5450a1b9edd1be2b9278bca8692426f928856d81c6a36764e4d59ff62f6f9ea
+size 3476137368
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..7709d59
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,404 @@
+{
+  "weight_map": {
+    "model.norm.weight": "model-0001-others-save_rank0.safetensors",
+    "lm_head.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-0001-others-save_rank0.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-0002-others-save_rank0.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-0003-others-save_rank0.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-0004-others-save_rank0.safetensors",
+    "model.embed_tokens.weight": "model-0004-others-save_rank0.safetensors"
+  },
+  "metadata": {}
+}
\ No newline at end of file
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..ac23c0a
--- /dev/null
+++ b/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
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..cd71f61
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..ddaf698
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..6c49fc6
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833