初始化项目，由ModelHub XC社区提供模型

Model: sensenova/SenseNova-SI-1.1-Qwen3-VL-8B
Source: Original Platform

.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
+*.ot 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
+
+merges.txt filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,118 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3-VL-8B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
+---
+
+**EN** | [中文](README_CN.md) 
+
+# SenseNova-SI: Scaling Spatial Intelligence with Multimodal Foundation Models
+
+<a href="https://github.com/OpenSenseNova/SenseNova-SI" target="_blank">
+    <img alt="Code" src="https://img.shields.io/badge/SenseNova_SI-Code-100000?style=flat-square&logo=github&logoColor=white" height="20" />
+</a>
+  <a href="https://arxiv.org/abs/2511.13719" target="_blank">
+      <img alt="arXiv" src="https://img.shields.io/badge/arXiv-SenseNova_SI-red?logo=arxiv" height="20" />
+  </a>
+<a href="https://github.com/EvolvingLMMs-Lab/EASI" target="_blank">
+    <img alt="Code" src="https://img.shields.io/badge/EASI-Code-100000?style=flat-square&logo=github&logoColor=white" height="20" />
+</a>
+<a href="https://easi.lmms-lab.com/leaderboard" target="_blank">
+    <img alt="Leaderboard" src="https://img.shields.io/badge/%F0%9F%A4%97%20_EASI-Leaderboard-ffc107?color=ffc107&logoColor=white" height="20" />
+</a>
+
+## Overview
+Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence.
+In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the **SenseNova-SI family**,
+built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel).
+We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M:
+eight million diverse data samples under a rigorous taxonomy of spatial capabilities.
+SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks: 68.7% on VSI-Bench, 43.3% on MMSI, 85.6% on MindCube,
+54.6% on ViewSpatial, and 50.1% on SITE, while maintaining strong general multimodal understanding (e.g., 84.9% on MMBench-En).
+More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training,
+analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. SenseNova-SI is an ongoing project, and this report will be updated continuously.
+All newly trained multimodal foundation models are publicly released to facilitate further research in this direction.
+*In the future, SenseNova-SI will be integrated with larger-scale in-house models.*
+
+## Release Information
+Currently, we build SenseNova-SI upon popular open-source foundation models to maximize compatibility with existing research pipelines.
+In this release, we present 
+[**SenseNova-SI-1.2-InternVL3-8B**](https://huggingface.co/sensenova/SenseNova-SI-1.2-InternVL3-8B), [**SenseNova-SI-1.1-Qwen2.5-VL-3B**](https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen2.5-VL-3B), [**SenseNova-SI-1.1-Qwen2.5-VL-7B**](https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen2.5-VL-7B), and [**SenseNova-SI-1.1-Qwen3-VL-8B**](https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen3-VL-8B), of which **SenseNova-SI-1.2-InternVL3-8B** achieve state-of-the-art performance among open-source models of comparable size across eight recent spatial intelligence benchmarks: 
+**VSI**, **MMSI**, **MindCube**, **ViewSpatial**, **SITE**, **BLINK**, **3DSRBench**, **EmbSpatial-Bench**.
+
+<table>
+  <thead>
+    <tr>
+      <th>Model</th>
+      <th>VSI</th>
+      <th>MMSI</th>
+      <th>MindCube-Tiny</th>
+      <th>ViewSpatial</th>
+      <th>SITE</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="background:#F2F0EF;font-weight:700;text-align:center;">
+      <td colspan="6"><em>Open-source Models (~8B)</em></td>
+    </tr>
+    <tr>
+      <td>InternVL3-8B</td><td>42.1</td><td>28.0</td><td>41.5</td><td>38.6</td><td>41.1</td>
+    </tr>
+    <tr>
+      <td>Qwen3-VL-8B-Instruct</td><td>57.9</td><td>31.1</td><td>29.4</td><td>42.2</td><td>45.8</td>
+    </tr>
+    <tr>
+      <td>BAGEL-7B-MoT</td><td>31.4</td><td>31.0</td><td>34.7</td><td>41.3</td><td>37.0</td>
+    </tr>
+    <tr>
+      <td>SpaceR-7B</td><td>41.5</td><td>27.4</td><td>37.9</td><td>35.8</td><td>34.2</td>
+    </tr>
+    <tr>
+      <td>ViLaSR-7B</td><td>44.6</td><td>30.2</td><td>35.1</td><td>35.7</td><td>38.7</td>
+    </tr>
+    <tr>
+      <td>VST-7B-SFT</td><td>60.6</td><td>32.0</td><td>39.7</td><td>50.5</td><td>39.6</td>
+    </tr>
+    <tr>
+      <td>Cambrian-S-7B</td><td>67.5</td><td>25.8</td><td>39.6</td><td>40.9</td><td>33.0</td>
+    </tr>
+    <tr>
+      <td><strong>SenseNova-SI-1.1-Qwen3-VL-8B</strong></td>
+      <td><strong>64.8</strong></td>
+      <td><strong>38.1</strong></td>
+      <td><strong>73.8</strong></td>
+      <td><strong>51.2</strong></td>
+      <td><strong>49.6</strong></td>
+    </tr>
+    <tr style="background:#F2F0EF;color:#6b7280;font-weight:600;text-align:center;">
+      <td colspan="6"><em>Proprietary Models</em></td>
+    </tr>
+    <tr style="color:#6b7280;">
+      <td>Gemini-2.5-pro-2025-06</td><td>53.5</td><td>38.0</td><td>57.6</td><td>46.0</td><td>57.0</td>
+    </tr>
+    <tr style="color:#6b7280;">
+      <td>Grok-4-2025-07-09</td><td>47.9</td><td>37.8</td><td>63.5</td><td>43.2</td><td>47.0</td>
+    </tr>
+    <tr style="color:#6b7280;">
+      <td>GPT-5-2025-08-07</td><td>55.0</td><td>41.8</td><td>56.3</td><td>45.5</td><td>61.8</td>
+    </tr>
+  </tbody>
+</table>
+
+## Evaluation
+
+To reproduce the benchmark results above, please refer to [EASI](https://easi.lmms-lab.com/leaderboard/) to evaluate SenseNova-SI on mainstream spatial intelligence benchmarks.
+
+
+## Citation
+
+```bib
+@InProceedings{sensenova-si,
+  title = {Scaling Spatial Intelligence with Multimodal Foundation Models},
+  author = {Cai, Zhongang and Wang, Ruisi and Gu, Chenyang and Pu, Fanyi and Xu, Junxiang and Wang, Yubo and Yin, Wanqi and Yang, Zhitao and Wei, Chen and Sun, Qingping and Zhou, Tongxi and Li, Jiaqi and Pang, Hui En and Qian, Oscar and Wei, Yukun and Lin, Zhiqian and Shi, Xuanke and Deng, Kewang and Han, Xiaoyang and Chen, Zukai and Fan, Xiangyu and Deng, Hanming and Lu, Lewei and Pan, Liang and Li, Bo and Liu, Ziwei and Wang, Quan and Lin, Dahua and Yang, Lei},
+  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year = {2026}
+}
+```

README_CN.md

@@ -0,0 +1,94 @@
+[EN](README.md) | **中文** 
+
+# SenseNova-SI: 探索空间智能在多模态基础模型上尺度效应
+
+<a href="https://github.com/OpenSenseNova/SenseNova-SI" target="_blank">
+    <img alt="Code" src="https://img.shields.io/badge/SenseNova_SI-Code-100000?style=flat-square&logo=github&logoColor=white" height="20" />
+</a>
+  <a href="https://arxiv.org/abs/2511.13719" target="_blank">
+      <img alt="arXiv" src="https://img.shields.io/badge/arXiv-SenseNova_SI-red?logo=arxiv" height="20" />
+  </a>
+<a href="https://github.com/EvolvingLMMs-Lab/EASI" target="_blank">
+    <img alt="Code" src="https://img.shields.io/badge/EASI-Code-100000?style=flat-square&logo=github&logoColor=white" height="20" />
+</a>
+<a href="https://easi.lmms-lab.com/leaderboard" target="_blank">
+    <img alt="Leaderboard" src="https://img.shields.io/badge/%F0%9F%A4%97%20_EASI-Leaderboard-ffc107?color=ffc107&logoColor=white" height="20" />
+</a>
+
+## 概览
+尽管多模态基础模型已取得显著进展，但在空间智能方面仍存在明显不足。
+本研究基于成熟的多模态基础，包括视觉理解模型（如Qwen3-VL、InternVL3）和统一理解生成模型（如Bagel），从尺度效应（Scaling）的视角构建了**SenseNova-SI系列模型**。
+我们采用系统化方法构建了包含800万样本的SenseNova-SI-8M数据集，通过严格的空间能力分类体系培养高性能、高鲁棒性的空间能力。
+该系列模型在多项空间智能基准测试中取得突破性表现：VSI-Bench 68.7%、MMSI 43.3%、MindCube 85.6%、ViewSpatial 54.6%、SITE 50.1%，同时保持强大的通用多模态理解能力（如MMBench-En 84.9%）。
+本研究进一步分析了数据规模的影响，揭示了多样化数据训练带来的涌现泛化能力，探讨了过拟合与语言捷径的风险，提出了空间思维链推理的初步研究，并验证了下游应用潜力。
+SenseNova-SI是一个持续迭代的项目，所有新训练的多模态空间智能基础模型均将陆续开源，以推动空间智能领域的研究发展。
+*后续 SenseNova-SI 将与更大规模的内部模型进行集成。*
+
+## 发布信息
+目前，我们基于流行的开源基础模型构建 SenseNova-SI，以最大化与现有研究流程的兼容性。
+在本次发布中，我们推出
+[**SenseNova-SI-1.2-InternVL3-8B**](https://huggingface.co/sensenova/SenseNova-SI-1.2-InternVL3-8B), 
+[**SenseNova-SI-1.1-Qwen2.5-VL-3B**](https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen2.5-VL-3B), 
+[**SenseNova-SI-1.1-Qwen2.5-VL-7B**](https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen2.5-VL-7B),
+与[**SenseNova-SI-1.1-Qwen3-VL-8B**](https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen3-VL-8B)，
+其中**SenseNova-SI-1.2-InternVL3-8B**在八个近期发布的空间智能基准测试（**VSI**、**MMSI**、**MindCube**、**ViewSpatial**、**SITE**、**BLINK**、**3DSRBench**、**EmbSpatial-Bench**）上，
+在同等模型规模下均取得了开源模型的最新最优性能（state-of-the-art）。
+
+<table>
+  <thead>
+    <tr>
+      <th>Model</th>
+      <th>VSI</th>
+      <th>MMSI</th>
+      <th>MindCube-Tiny</th>
+      <th>ViewSpatial</th>
+      <th>SITE</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="background:#F2F0EF;font-weight:700;text-align:center;">
+      <td colspan="6"><em>Open-source Models (~8B)</em></td>
+    </tr>
+    <tr>
+      <td>InternVL3-8B</td><td>42.1</td><td>28.0</td><td>41.5</td><td>38.6</td><td>41.1</td>
+    </tr>
+    <tr>
+      <td>Qwen3-VL-8B-Instruct</td><td>57.9</td><td>31.1</td><td>29.4</td><td>42.2</td><td>45.8</td>
+    </tr>
+    <tr>
+      <td>BAGEL-7B-MoT</td><td>31.4</td><td>31.0</td><td>34.7</td><td>41.3</td><td>37.0</td>
+    </tr>
+    <tr>
+      <td>SpaceR-7B</td><td>41.5</td><td>27.4</td><td>37.9</td><td>35.8</td><td>34.2</td>
+    </tr>
+    <tr>
+      <td>ViLaSR-7B</td><td>44.6</td><td>30.2</td><td>35.1</td><td>35.7</td><td>38.7</td>
+    </tr>
+    <tr>
+      <td>VST-7B-SFT</td><td>60.6</td><td>32.0</td><td>39.7</td><td>50.5</td><td>39.6</td>
+    </tr>
+    <tr>
+      <td>Cambrian-S-7B</td><td>67.5</td><td>25.8</td><td>39.6</td><td>40.9</td><td>33.0</td>
+    </tr>
+    <tr>
+      <td><strong>SenseNova-SI-1.1-Qwen3-VL-8B</strong></td>
+      <td><strong>64.8</strong></td>
+      <td><strong>38.1</strong></td>
+      <td><strong>73.8</strong></td>
+      <td><strong>51.2</strong></td>
+      <td><strong>49.6</strong></td>
+    </tr>
+    <tr style="background:#F2F0EF;color:#6b7280;font-weight:600;text-align:center;">
+      <td colspan="6"><em>Proprietary Models</em></td>
+    </tr>
+    <tr style="color:#6b7280;">
+      <td>Gemini-2.5-pro-2025-06</td><td>53.5</td><td>38.0</td><td>57.6</td><td>46.0</td><td>57.0</td>
+    </tr>
+    <tr style="color:#6b7280;">
+      <td>Grok-4-2025-07-09</td><td>47.9</td><td>37.8</td><td>63.5</td><td>43.2</td><td>47.0</td>
+    </tr>
+    <tr style="color:#6b7280;">
+      <td>GPT-5-2025-08-07</td><td>55.0</td><td>41.8</td><td>56.3</td><td>45.5</td><td>61.8</td>
+    </tr>
+  </tbody>
+</table>

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 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.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' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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' }}
+{%- endif %}

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "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,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89451db9e1af54dec391a6f6d2940076f456170fe86e10b3c1f864fca167c8f4
+size 4998056552

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23dbacc3a3bd35d5a34e4a2f3a5de24f571d12d4a1527a2b0809850d63fca11d
+size 4915962464

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba07ba91bc832768d0226a33f1be2e075f4f234788e08b3c5b1b3d32c082848c
+size 4915962496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc10ebb23be7bfc1fdea636c48730fc730e4093f5f3d8285d0554f30074809fc
+size 2704357976

model.safetensors.index.json

@@ -0,0 +1,758 @@
+{
+  "metadata": {
+    "total_parameters": 8767123696,
+    "total_size": 17534247392
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": 147456,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 147456,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 147456,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}