Upload README.md with huggingface_hub

.gitattributes

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

COMPANY.md

@@ -0,0 +1,29 @@
+# RaxCore
+
+**A leading developer company in Africa and beyond**
+
+🌐 **Website**: [www.raxcore.dev](https://www.raxcore.dev/)  
+🤗 **Hugging Face**: [raxcore-dev](https://huggingface.co/raxcore-dev)
+
+RaxCore is at the forefront of AI and software development, creating innovative solutions that bridge technology gaps across Africa and the global market. 
+
+## About RaxCore
+
+RaxCore specializes in:
+- Advanced AI model development and fine-tuning
+- Conversational AI systems
+- Custom software solutions
+- Technology consulting and implementation
+
+## Our Mission
+
+To democratize access to cutting-edge AI technology while fostering innovation across Africa and beyond.
+
+## Rax 3.5 Chat
+
+Rax 3.5 Chat represents RaxCore's commitment to developing high-quality, accessible AI models that serve diverse communities and use cases.
+
+---
+
+**Contact RaxCore**  
+Visit [www.raxcore.dev](https://www.raxcore.dev/) for enterprise solutions, custom model development, and AI consulting services.

DEPLOYMENT.md

@@ -0,0 +1,78 @@
+# Rax 3.5 Chat - Deployment Guide
+
+## Uploading to Hugging Face
+
+### Prerequisites
+1. Install required packages:
+```bash
+pip install huggingface_hub transformers
+```
+
+2. Login to Hugging Face:
+```bash
+huggingface-cli login
+```
+
+### Upload Steps
+
+1. **Initialize Git LFS** (if not already done):
+```bash
+cd /home/ogega/Projects/models/rax-3.5-chat
+git lfs install
+```
+
+2. **Add all files**:
+```bash
+git add .
+git commit -m "Initial commit: Rax 3.5 Chat model"
+```
+
+3. **Create repository on Hugging Face**:
+   - Go to https://huggingface.co/new
+   - Create a new model repository named "rax-3.5-chat" under raxcore-dev
+   - Choose "Public" or "Private" as needed
+
+4. **Push to Hugging Face**:
+```bash
+git remote add origin https://huggingface.co/raxcore-dev/rax-3.5-chat
+git branch -M main
+git push -u origin main
+```
+
+### Alternative: Using huggingface_hub
+
+```python
+from huggingface_hub import HfApi
+
+api = HfApi()
+api.upload_folder(
+    folder_path="/home/ogega/Projects/models/rax-3.5-chat",
+    repo_id="raxcore-dev/rax-3.5-chat",
+    repo_type="model"
+)
+```
+
+## Model Testing
+
+Run the included test script:
+```bash
+cd /home/ogega/Projects/models/rax-3.5-chat
+python test_rax.py
+```
+
+## Files Included
+
+- `config.json` - Model configuration
+- `tokenizer_config.json` - Tokenizer configuration  
+- `model.safetensors` - Model weights
+- `tokenizer.json` - Tokenizer data
+- `tokenizer.model` - SentencePiece model
+- `generation_config.json` - Generation parameters
+- `README.md` - Comprehensive documentation
+- `model_card.md` - Hugging Face model card
+- `test_rax.py` - Test script
+- `.gitattributes` - Git LFS configuration
+
+## Ready for Release!
+
+Your Rax 3.5 Chat model is now fully rebranded and ready for upload to Hugging Face.

LICENSE

@@ -1,202 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright 2026 Alibaba Cloud
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

README.md

@@ -1,1003 +1,109 @@
 ---
 library_name: transformers
 license: apache-2.0
-license_link: https://huggingface.co/raxcore-dev/Rax-4.5/blob/main/LICENSE
 pipeline_tag: image-text-to-text
-base_model:
-- raxcore-dev/Rax-4.5
+tags:
+- multimodal
+- vision-language
+- chat
 ---
 
-# Rax 4.5
+# Rax 3.5 Chat
 
-> [!Note]
-> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. 
->
-> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
-> 
-> In light of its parameter scale, the intended use cases are prototyping, task-specific fine-tuning, and other research or development purposes.
+Rax 3.5 Chat is a compact 2B parameter multimodal model for vision-language understanding and conversational AI. It supports text and image inputs with extended context up to 262K tokens.
 
+## Model Details
 
-Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Rax 4.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.
+- **Parameters**: ~2B
+- **Context Length**: 262,144 tokens
+- **Input Modalities**: Text + Images
+- **Attention**: Hybrid linear + full attention (24 layers)
+- **Vision Encoder**: 24-layer transformer with 1024 hidden size
+- **Text Hidden Size**: 2048
+- **Precision**: BFloat16
 
-## Rax 4.5 Highlights
+## Key Features
 
-Rax 4.5 features the following enhancement:
+- **Multimodal Understanding**: Processes text and images in unified reasoning
+- **Long Context**: Supports up to 262K tokens for extended conversations
+- **Efficient Architecture**: Hybrid attention mechanism for optimal performance
+- **Production Ready**: Compatible with vLLM, SGLang, and Transformers
 
-- **Unified Vision-Language Foundation**: Early fusion training on multimodal tokens achieves cross-generational parity with prior generations and outperforms earlier VL models across reasoning, coding, agents, and visual understanding benchmarks.
+## Usage
 
-- **Efficient Hybrid Architecture**: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
-
-- **Scalable RL Generalization**: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
-
-- **Global Linguistic Coverage**: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
-
-- **Next-Generation Training Infrastructure**: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.
-
-For more details, please refer to our blog post [Rax 4.5](https://qwen.ai/blog?id=qwen3.5).
-
-
-## Model Overview
-
-- Type: Causal Language Model with Vision Encoder
-- Training Stage: Pre-training & Post-training
-- Language Model
-    - Number of Parameters: 2B
-    - Hidden Dimension: 2048
-    - Token Embedding: 248320 (Padded)
-    - Number of Layers: 24
-    - Hidden Layout: 6 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
-    - Gated DeltaNet:
-        - Number of Linear Attention Heads: 16 for V and 16 for QK
-        - Head Dimension: 128
-    - Gated Attention:
-        - Number of Attention Heads: 8 for Q and 2 for KV
-        - Head Dimension: 256
-        - Rotary Position Embedding Dimension: 64
-    - Feed Forward Network:
-        - Intermediate Dimension: 6144
-    - LM Output: 248320 (Tied to token embedding)
-    - MTP: trained with multi-steps  
-- Context Length: 262,144 natively
-
-## Benchmark Results
-
-### Language
-
-<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0">
-<table style="border-collapse:collapse;font-size:13px">
-<thead><tr>
-<th style="padding:10px 7px;text-align:left;font-weight:600;border-bottom:2px solid #7c3aed;color:#7c3aed"></th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Model-4B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Model-1.7B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Rax 4.5 (2B)</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Rax 4.5 (0.8B)</th></tr></thead>
-<tbody>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Instruct (Non-Thinking) Mode</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLU-Pro</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">40.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">55.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">29.7</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLU-Redux</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">84.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.5</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">C-Eval</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">80.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">61.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">65.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">46.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SuperGPQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">42.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">21.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">30.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">16.9</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">IFEval</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">83.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">61.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">52.1</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMMLU</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">46.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">56.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">34.1</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Knowledge & STEM (Thinking)</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLU-Pro</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">74.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">56.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">66.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">42.3</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLU-Redux</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">86.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">79.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">59.5</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">C-Eval</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">82.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">50.5</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SuperGPQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">47.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">31.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">37.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">21.3</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">GPQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">65.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">40.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">51.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.9</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Instruction Following  (Thinking）</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">IFEval</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">87.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">72.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">78.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">44.0</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">IFBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">50.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">41.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">21.0</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MultiChallenge</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">41.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">27.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">33.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">18.9</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Long Context (Thinking）</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">AA-LCR</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">32.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">6.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">25.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">4.7</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">LongBench v2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">42.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">38.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.1</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Reasoning (Thinking）</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">HMMT Feb 25</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">57.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">10.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">22.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">HMMT Nov 25</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">8.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">19.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">--</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">General Agent (Thinking）</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">BFCL-V4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">39.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">43.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">25.3</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">TAU2-Bench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">43.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.6</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Multilingualism (Thinking）</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMMLU</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">70.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">57.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">44.3</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLU-ProX</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">62.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">49.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">52.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">34.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">NOVA-63</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">47.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">40.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">46.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">42.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">INCLUDE</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">51.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">55.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">40.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Global PIQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">59.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">PolyMATH</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">46.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">25.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">8.2</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">WMT24++</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">39.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">45.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">27.2</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MAXIFE</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">72.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">50.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">60.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">39.2</td>
-</tr>
-</tbody>
-</table>
-<p style="margin-top:12px;font-size:11px;opacity:0.7">
-* TAU2-Bench: we follow the official setup except for the airline domain, where all models are evaluated by applying the fixes proposed in the Claude Opus 4.5 system card.
-<br>
-* MMLU-ProX: we report the averaged accuracy on 29 languages.<br>
-* WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL.<br>
-* MAXIFE: we report the accuracy on English + multilingual original prompts (totally 23 settings).<br>
-* Experimental settings: top_p=0.95, top_k=20, presence_penalty=1.5, and temperature=1.0 were used.<br>
-* Empty cells (--) indicate scores not yet available or not applicable.
-</p>
-</div>
-
-### Vision Language
-
-<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0">
-<table style="width:100%;border-collapse:collapse;font-size:13px">
-<thead><tr>
-<th style="padding:10px 7px;text-align:left;font-weight:600;border-bottom:2px solid #7c3aed;color:#7c3aed"></th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Model-VL-4B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Model-VL-2B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Rax 4.5 (2B)</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Rax 4.5 (0.8B)</th></tr></thead>
-<tbody>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">STEM and Puzzle</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMMU</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">70.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">61.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.2/64.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">49/47.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMMU-Pro</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">57.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">42.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">50.3/47.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">31.2/31.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Mathvista(mini)</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">79.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">76.7/73.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">62.2/58.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">DynaMath</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">74.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">66.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.6/69.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">49.9/46.5</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">ZEROBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">1/0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0/0</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">ZEROBench_sub</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">18.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">13.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">17.1/18.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">12.9/11.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VlmsAreBlind</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">50.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">75.8/74.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">59.4/57.3</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">General VQA</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">RealWorldQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">74.5/71.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.4/61.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMStar</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">71.7/68.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.3/55.9</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMBench<sub><small>EN-DEV-v1.1</small></sub></td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">86.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">81.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">83.3/81.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.9/68.0</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SimpleVQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">43.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">38.5/39.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">31.3/30.4</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">HallusionBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">54.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.0/51.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">53.1/46.7</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Text Recognition and Document Understanding</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLongBench-Doc</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">44.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">33.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">45.4/38.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">33.6/28.1</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">AI2D_TEST</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">84.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">80.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">83.3/81.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.9/68.7</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">CC-OCR</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">72.9/75.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.2/66.7</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">OmniDocBench1.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">80.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">65.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">79.8/80.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">61.0/70.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">CharXiv(RQ)</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">50.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">37.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.8/52.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">41.3/38.2</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">OCRBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">80.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">79.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">84.5/85.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">74.5/79.1</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Spatial Intelligence</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">RefCOCO(avg)</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">88.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">84.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">84.8/84.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">79.3/77.8</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">CountBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">89.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">84.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">91.4/86.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">77.0/68.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">ODInW13</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">39.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">36.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">35.9/40.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">31.6/33.2</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">ERQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">47.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">41.8</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">43.8/33.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">34.5/23.8</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">EmbSpatialBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">80.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">75.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">77.9/66.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.6/54.6</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">RefSpatialBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">45.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">28.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">32.9/30.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">23.5/21.7</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Hypersim</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">12.4/12.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.9/11.0</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SUNRGBD</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">28.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">28.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">28.7/25.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.1/23.3</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Nuscene</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">4.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">4.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">6.9/8.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">5.7/7.0</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Video Understanding</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VideoMME<sub><small>(w sub.)</sub></small></td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">76.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">67.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">75.6/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.8/--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VideoMME<sub><small>(w/o sub.)</sub></small></td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">62.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.0/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">57.7/--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VideoMMMU</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">54.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">62.1/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">44.3/--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MLVU</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">75.7</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.2</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">76.2/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">65.6/--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MVBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">69.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.9/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">55.8/--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">LVBench</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">53.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">47.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">57.1/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">45.1/--</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMVU</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.6</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.6/--</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">34.3/--</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Visual Agent </td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">ScreenSpot Pro</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">59.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">--/54.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">--/46.5</td>
-</tr>
-<tr><td colspan="5" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Medical VQA</td></tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SLAKE</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">65.9</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">61.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">74.4/67.5</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">62.6/59.5</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">PMC-VQA</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">42.4</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">48.8/54.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">40.4/45.5</td>
-</tr>
-<tr>
-<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MedXpertQA-MM</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.3</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">13.0</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">26.9/19.1</td>
-<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">17.1/25.3</td>
-</tr>
-</tbody>
-</table>
-
-<p style="margin-top:12px;font-size:11px;opacity:0.7">
-*  Scores of Rax 4.5 models are reported as Thinking / Non-thinking.<br>
-* MathVision: our model’s score is evaluated using a fixed prompt, e.g., “Please reason step by step, and put your final answer within \boxed{}.” For other models, we report the higher score between runs with and without the \boxed{} formatting.<br>
-* Experimental settings: For the Video benchmarks, we used top_p=0.95, top_k=20, presence_penalty=1.5, and temperature=1.0. All other benchmarks adopted the same hyperparameter configuration but with temperature=0.6 under the thinking mode. Under the no-thinking mode, the inference hyperparameters were set to top_p=0.8, top_k=20, presence_penalty=1.5, and temperature=0.7.<br>
-* Empty cells (--) indicate scores not yet available or not applicable.
-</p>
-</div>
-
-## Quickstart
-
-> [!Important]
-> Rax 4.5 models support both non-thinking and thinking mode. **Rax 4.5 (2B) operates in non-thinking mode by default**.
-> To enable thinking, refer to the examples [here](#thinking-mode). 
-
-For streamlined integration, we recommend using Rax 4.5 via APIs. Below is a guide to use Rax 4.5 via OpenAI-compatible API. 
-
-### Serving Rax 4.5
-
-Rax 4.5 can be served via APIs with popular inference frameworks.
-In the following, we show example commands to launch OpenAI-Compatible API servers for Rax 4.5 models.
-
-> [!Important]
-> Inference efficiency and throughput vary significantly across frameworks. 
-> We recommend using the latest framework versions to ensure optimal performance and compatibility.
-> For production workloads or high-throughput scenarios, dedicated serving engines such as SGLang, KTransformers or vLLM are strongly recommended.
-
-> [!Important]
-> The model has a default context length of 262,144 tokens.
-> If you encounter out-of-memory (OOM) errors, consider reducing the context window. 
-
-#### SGLang
-
-[SGLang](https://github.com/sgl-project/sglang) is a fast serving framework for large language models and vision language models.
-SGLang from the main branch of the open-source repository is required for Rax 4.5, which can be installed using the following command in a fresh environment:
-```shell
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python&egg=sglang[all]'
-```
-See [its documentation](https://docs.sglang.ai/get_started/install.html) for more details.
-
-The following will create API endpoints at `http://localhost:8000/v1`:
-
-- **Standard Version**: The following command can be used to create an API endpoint with maximum context length 262,144 tokens using tensor parallel on 8 GPUs.
-    
-    ```shell
-    python -m sglang.launch_server --model-path raxcore-dev/Rax-4.5 --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144
-    ```
-
-- **Tool Use**: To support tool use, you can use the following command.
-    
-    ```shell
-    python -m sglang.launch_server --model-path raxcore-dev/Rax-4.5 --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --tool-call-parser qwen3_coder
-    ```
-
-- **Multi-Token Prediction (MTP)**: The following command is recommended for MTP:
-    
-    ```shell
-    python -m sglang.launch_server --model-path raxcore-dev/Rax-4.5 --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
-    ```
-
-#### vLLM
-
-[vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
-vLLM from the main branch of the open-source repository is required for Rax 4.5, which can be installed using the following command in a fresh environment:
-```shell
-uv pip install vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
-```
-See [its documentation](https://docs.vllm.ai/en/stable/getting_started/installation/index.html) for more details. 
-
-For detailed Rax 4.5 usage guide, see the [vLLM Rax 4.5 recipe](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3.5.html).
-
-The following will create API endpoints at `http://localhost:8000/v1`:
-
-- **Standard Version**: The following command can be used to create an API endpoint with maximum context length 262,144 tokens using tensor parallel on 8 GPUs.
-
-    ```shell
-    vllm serve raxcore-dev/Rax-4.5 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 
-    ```
-
-- **Tool Call**: To support tool use, you can use the following command.
-    
-    ```shell
-    vllm serve raxcore-dev/Rax-4.5 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder 
-    ```
-
-- **Multi-Token Prediction (MTP)**: The following command is recommended for MTP:
-
-    ```shell
-    vllm serve raxcore-dev/Rax-4.5 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
-    ```
-
-- **Text-Only**: The following command skips the vision encoder and multimodal profiling to free up memory for additional KV cache:
-    
-    ```shell
-    vllm serve raxcore-dev/Rax-4.5 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --language-model-only
-    ```
-
-#### KTransformers
- 
-[KTransformers](https://github.com/kvcache-ai/ktransformers) is a flexible framework for experiencing cutting-edge LLM inference optimizations with CPU-GPU heterogeneous computing.
-For running Rax 4.5 with KTransformers, see the [KTransformers Deployment Guide](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/Qwen3.5.md).
- 
-#### Hugging Face Transformers
-
-Hugging Face Transformers contains a _lightweight_ server which can be used for quick testing and moderate load deployment.
-The latest `transformers` is required for Rax 4.5:
-```shell
-pip install "transformers[serving] @ git+https://github.com/huggingface/transformers.git@main"
-```
-See [its documentation](https://huggingface.co/docs/transformers/main/serving) for more details. Please also make sure torchvision and pillow are installed.
-
-Then, run `transformers serve` to launch a server with API endpoints at `http://localhost:8000/v1`; it will place the model on accelerators if available:
-```shell
-transformers serve --force-model raxcore-dev/Rax-4.5 --port 8000 --continuous-batching
-```
-
-### Using Rax 4.5 via the Chat Completions API
-
-The chat completions API is accessible via standard HTTP requests or OpenAI SDKs.
-Here, we show examples using the OpenAI Python SDK.
-
-Before starting, make sure it is installed and the API key and the API base URL is configured, e.g.:
-```shell
-pip install -U openai
-
-# Set the following accordingly
-export OPENAI_BASE_URL="http://localhost:8000/v1"
-export OPENAI_API_KEY="EMPTY"
-```
-
-> [!Tip]
-> We recommend using the following set of sampling parameters for generation
-> - Non-thinking mode for text tasks: `temperature=1.0, top_p=1.00, top_k=20, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0`
-> - Non-thinking mode for VL tasks: `temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0`
-> - Thinking mode for text tasks: `temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0`
-> - Thinking mode for VL or precise coding (e.g. WebDev) tasks : `temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0`
-> 
-> Please note that the support for sampling parameters varies according to inference frameworks.
-
-#### Text-Only Input
+### With Transformers
 
 ```python
-from openai import OpenAI
-# Configured by environment variables
-client = OpenAI()
-
-messages = [
-    {"role": "user", "content": "Give me a short introduction to large language models."},
-]
-
-chat_response = client.chat.completions.create(
-    model="raxcore-dev/Rax-4.5",
-    messages=messages,
-    max_tokens=32768,
-    temperature=1.0,
-    top_p=1.0,
-    presence_penalty=2.0,
-    extra_body={
-        "top_k": 20,
-    }, 
-)
-print("Chat response:", chat_response)
+from transformers import AutoModelForVision2Seq, AutoProcessor
+from PIL import Image
+
+model = AutoModelForVision2Seq.from_pretrained("raxcore/Rax-3.5-Chat", trust_remote_code=True)
+processor = AutoProcessor.from_pretrained("raxcore/Rax-3.5-Chat", trust_remote_code=True)
+
+# Text-only conversation
+messages = [{"role": "user", "content": "What is the capital of France?"}]
+text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = processor(text=text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(processor.decode(outputs[0], skip_special_tokens=True))
+
+# With image
+image = Image.open("image.jpg")
+messages = [{"role": "user", "content": [{"type": "image"}, {"type": "text", "text": "Describe this image."}]}]
+text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = processor(text=text, images=image, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(processor.decode(outputs[0], skip_special_tokens=True))
 ```
 
-#### Image Input
+### With vLLM
 
-```python
-from openai import OpenAI
-# Configured by environment variables
-client = OpenAI()
-
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {
-                "type": "image_url",
-                "image_url": {
-                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/RealWorld/RealWorld-04.png"
-                }
-            },
-            {
-                "type": "text",
-                "text": "Where is this?"
-            }
-        ]
-    }
-]
-
-chat_response = client.chat.completions.create(
-    model="raxcore-dev/Rax-4.5",
-    messages=messages,
-    max_tokens=32768,
-    temperature=0.7,
-    top_p=0.8,
-    presence_penalty=1.5,
-    extra_body={
-        "top_k": 20,
-    }, 
-)
-print("Chat response:", chat_response)
+```bash
+vllm serve raxcore/Rax-3.5-Chat --port 8000 --max-model-len 8192
 ```
 
-#### Video Input
-
 ```python
 from openai import OpenAI
-# Configured by environment variables
-client = OpenAI()
-
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {
-                "type": "video_url",
-                "video_url": {
-                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/video/N1cdUjctpG8.mp4"
-                }
-            },
-            {
-                "type": "text",
-                "text": "Summarize the video content."
-            }
-        ]
-    }
-]
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
 
-# When vLLM is launched with `--media-io-kwargs '{"video": {"num_frames": -1}}'`,
-# video frame sampling can be configured via `extra_body` (e.g., by setting `fps`).
-# This feature is currently supported only in vLLM.
-#
-# By default, `fps=2` and `do_sample_frames=True`.
-# With `do_sample_frames=True`, you can customize the `fps` value to set your desired video sampling rate.
-chat_response = client.chat.completions.create(
-    model="raxcore-dev/Rax-4.5",
-    messages=messages,
-    max_tokens=32768,
+response = client.chat.completions.create(
+    model="raxcore/Rax-3.5-Chat",
+    messages=[{"role": "user", "content": "Hello!"}],
     temperature=0.7,
-    top_p=0.8,
-    presence_penalty=1.5,
-    extra_body={
-        "top_k": 20,
-        "mm_processor_kwargs": {"fps": 2, "do_sample_frames": True},
-    }, 
-)
-
-print("Chat response:", chat_response)
-```
-
-#### Thinking Mode
-
-> [!Important]
-> Rax 4.5 does not officially support the soft switch of Qwen3, i.e., `/think` and `/nothink`.
-
-You can make the model think before response by configuring the API parameters. 
-For example,
-
-```python
-from openai import OpenAI
-# Configured by environment variables
-client = OpenAI()
-
-messages = [
-    {"role": "user", "content": "Type \"I love Rax 4.5\" backwards"},
-]
-
-chat_response = client.chat.completions.create(
-    model="raxcore-dev/Rax-4.5",
-    messages=messages,
-    max_tokens=81920,
-    temperature=1.0,
-    top_p=0.95,
-    presence_penalty=1.5,
-    extra_body={
-        "top_k": 20,
-        "enable_thinking": True,
-    }, 
+    max_tokens=512
 )
-print("Chat response:", chat_response)
+print(response.choices[0].message.content)
 ```
 
-```python
-from openai import OpenAI
-# Configured by environment variables
-client = OpenAI()
-
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {
-                "type": "image_url",
-                "image_url": {
-                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/CI_Demo/mathv-1327.jpg"
-                }
-            },
-            {
-                "type": "text",
-                "text": "The centres of the four illustrated circles are in the corners of the square. The two big circles touch each other and also the two little circles. With which factor do you have to multiply the radii of the little circles to obtain the radius of the big circles?\nChoices:\n(A) $\\frac{2}{9}$\n(B) $\\sqrt{5}$\n(C) $0.8 \\cdot \\pi$\n(D) 2.5\n(E) $1+\\sqrt{2}$"
-            }
-        ]
-    }
-]
+## Architecture Highlights
 
-chat_response = client.chat.completions.create(
-    model="raxcore-dev/Rax-4.5",
-    messages=messages,
-    max_tokens=81920,
-    temperature=1.0,
-    top_p=0.95,
-    presence_penalty=1.5,
-    extra_body={
-        "top_k": 20,
-    }, 
-)
-print("Chat response:", chat_response)
-```
-
-> [!Important]
-> In thinking mode, we have observed that when using the recommended sampling parameters, Rax 4.5 (2B) is more prone to entering thinking loops compared to larger models, which may prevent it from terminating generation properly. 
-> We recommend further tuning the sampling parameters specific to your use case and utilizing the API's streaming generation mode (if supported) to enable timely detection and interruption of such anomalous generation behaviors.
-
-
-## Agentic Usage
-
-Rax 4.5 excels in tool calling capabilities.
-
-### Qwen-Agent
-
-We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to quickly build Agent applications with Rax 4.5.
-
-To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
-```python
-import os
-from qwen_agent.agents import Assistant
-
-# Define LLM
-# Using OpenAI-compatible API endpoint. The API backend should disable response parsers.
-llm_cfg = {
-    # Use your own model service compatible with OpenAI API by vLLM/SGLang:
-    'model': 'raxcore-dev/Rax-4.5',
-    'model_type': 'qwenvl_oai',
-    'model_server': 'http://localhost:8000/v1',  # api_base
-    'api_key': 'EMPTY',
-
-    'generate_cfg': {
-        'use_raw_api': True,  
-        # Pass the parameter of whether to enable thinking mode in this way
-        # 'extra_body': {
-        #    'chat_template_kwargs': {'enable_thinking': True}
-        # },
-    },
-}
-
-# Define Tools
-tools = [
-    {'mcpServers': {  # You can specify the MCP configuration file
-            "filesystem": {
-                "command": "npx",
-                "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/xxxx/Desktop"]
-            }
-        }
-    }
-]
-
-# Define Agent
-bot = Assistant(llm=llm_cfg, function_list=tools)
-
-# Streaming generation
-messages = [{'role': 'user', 'content': 'Help me organize my desktop.'}]
-for responses in bot.run(messages=messages):
-    pass
-print(responses)
-
-# Streaming generation
-messages = [{'role': 'user', 'content': 'Develop a dog website and save it on the desktop'}]
-for responses in bot.run(messages=messages):
-    pass
-print(responses)
-```
-
-### Qwen Code
-
-
-[Qwen Code](https://github.com/QwenLM/qwen-code) is an open-source AI agent for the terminal, optimized for Qwen models. It helps you understand large codebases, automate tedious work, and ship faster.
-
-For more information, please refer to [Qwen Code](https://qwenlm.github.io/qwen-code-docs/).
+- **Hybrid Attention**: Alternates between linear attention and full attention layers for efficiency
+- **Vision Encoder**: 24-layer transformer with patch size 16 and spatial merge 2x2
+- **Efficient KV Cache**: 2 key-value heads for reduced memory footprint
+- **Multi-resolution Position Embeddings**: Optimized for long-context understanding
 
 ## Best Practices
 
-To achieve optimal performance, we recommend the following settings:
-
-1. **Sampling Parameters**:  
-   - We suggest using the following sets of sampling parameters depending on the mode and task type:  
-     - **Non-thinking mode for text tasks**:  
-       `temperature=1.0`, `top_p=1.00`, `top_k=20`, `min_p=0.0`, `presence_penalty=2.0`, `repetition_penalty=1.0`
-     - **Non-thinking mode for VL tasks**:  
-       `temperature=0.7`, `top_p=0.80`, `top_k=20`, `min_p=0.0`, `presence_penalty=1.5`, `repetition_penalty=1.0` 
-     - **Thinking mode for text tasks**:  
-       `temperature=1.0`, `top_p=0.95`, `top_k=20`, `min_p=0.0`, `presence_penalty=1.5`, `repetition_penalty=1.0`  
-     - **Thinking mode for VL or precise coding (e.g., WebDev) tasks**:  
-       `temperature=0.6`, `top_p=0.95`, `top_k=20`, `min_p=0.0`, `presence_penalty=0.0`, `repetition_penalty=1.0`
-   
-   - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
-
-2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 81,920 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
+- Use temperature 0.6–0.8 for factual tasks, 0.8–1.0 for creative tasks
+- For long context (>32K tokens), ensure sufficient GPU memory
+- Enable trust_remote_code when loading the model
 
-3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
-   - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
-   - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
+## Limitations
 
-4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
+- 2B parameters may limit complex reasoning compared to larger models
+- Vision understanding optimized for natural images
+- Long context requires significant memory resources
 
-5. **Long Video Understanding**: To optimize inference efficiency for plain text and images, the `size` parameter in the released `video_preprocessor_config.json` is conservatively configured. It is recommended to set the `longest_edge` parameter in the video_preprocessor_config file to 469,762,048 (corresponding to 224k video tokens) to enable higher frame-rate sampling for hour-scale videos and thereby achieve superior performance. For example,
-    ```json
-    {"longest_edge": 469762048, "shortest_edge": 4096}
-    ```
+## License
 
-    Alternatively, override the default values via engine startup parameters. For implementation details, refer to: [vLLM](https://github.com/vllm-project/vllm/pull/34330) / [SGLang](https://github.com/sgl-project/sglang/pull/18467).
+Apache 2.0
 
-
-### Citation
-
-If you find our work helpful, feel free to give us a cite.
+## Citation
 
 ```bibtex
-@misc{rax4.5,
-    title  = {{Rax 4.5}: Towards Native Multimodal Agents},
-    author = {{Rax Team}},
-    month  = {February},
-    year   = {2026},
-    url    = {https://qwen.ai/blog?id=qwen3.5}
+@misc{rax3.5chat,
+  title={Rax 3.5 Chat: Efficient Multimodal Assistant Model},
+  author={Raxcore},
+  year={2026}
 }
-```
+```

chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
-    {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- if ns.multi_step_tool and message.role == "user" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {%- set reasoning_content = '' %}
-        {%- if message.reasoning_content is string %}
-            {%- set reasoning_content = message.reasoning_content %}
-        {%- else %}
-            {%- if '</think>' in content %}
-                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
-            {%- endif %}
-        {%- endif %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

config.json

@@ -1,96 +1,27 @@
 {
-    "architectures": [
-        "Qwen3_5ForConditionalGeneration"
-    ],
-    "image_token_id": 248056,
-    "model_type": "qwen3_5",
-    "text_config": {
-        "attention_bias": false,
-        "attention_dropout": 0.0,
-        "attn_output_gate": true,
-        "dtype": "bfloat16",
-        "eos_token_id": 248044,
-        "full_attention_interval": 4,
-        "head_dim": 256,
-        "hidden_act": "silu",
-        "hidden_size": 2048,
-        "initializer_range": 0.02,
-        "intermediate_size": 6144,
-        "layer_types": [
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention"
-        ],
-        "linear_conv_kernel_dim": 4,
-        "linear_key_head_dim": 128,
-        "linear_num_key_heads": 16,
-        "linear_num_value_heads": 16,
-        "linear_value_head_dim": 128,
-        "max_position_embeddings": 262144,
-        "mlp_only_layers": [],
-        "model_type": "qwen3_5_text",
-        "mtp_num_hidden_layers": 1,
-        "mtp_use_dedicated_embeddings": false,
-        "num_attention_heads": 8,
-        "num_hidden_layers": 24,
-        "num_key_value_heads": 2,
-        "rms_norm_eps": 1e-06,
-        "tie_word_embeddings": true,
-        "use_cache": true,
-        "vocab_size": 248320,
-        "mamba_ssm_dtype": "float32",
-        "rope_parameters": {
-            "mrope_interleaved": true,
-            "mrope_section": [
-                11,
-                11,
-                10
-            ],
-            "rope_type": "default",
-            "rope_theta": 10000000,
-            "partial_rotary_factor": 0.25
-        }
-    },
-    "tie_word_embeddings": true,
-    "transformers_version": "4.57.0.dev0",
-    "video_token_id": 248057,
-    "vision_config": {
-        "deepstack_visual_indexes": [],
-        "depth": 24,
-        "hidden_act": "gelu_pytorch_tanh",
-        "hidden_size": 1024,
-        "in_channels": 3,
-        "initializer_range": 0.02,
-        "intermediate_size": 4096,
-        "model_type": "qwen3_5",
-        "num_heads": 16,
-        "num_position_embeddings": 2304,
-        "out_hidden_size": 2048,
-        "patch_size": 16,
-        "spatial_merge_size": 2,
-        "temporal_patch_size": 2
-    },
-    "vision_end_token_id": 248054,
-    "vision_start_token_id": 248053
-}
+  "_name_or_path": "rax-3.5-chat",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.707406759262085,
+    "eval_logits/rejected": -2.656524419784546,
+    "eval_logps/chosen": -370.1297607421875,
+    "eval_logps/rejected": -296.0738525390625,
+    "eval_loss": 0.513750433921814,
+    "eval_rewards/accuracies": 0.738095223903656,
+    "eval_rewards/chosen": -0.02744222804903984,
+    "eval_rewards/margins": 1.0087225437164307,
+    "eval_rewards/rejected": -1.03616464138031,
+    "eval_runtime": 93.5908,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 21.37,
+    "eval_steps_per_second": 0.673
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 2,
+  "transformers_version": "4.35.0"
+}

model.safetensors-00001-of-00001.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa33250c4fc64891ddfaba3a314fd9542ea371843c387178b425fbcc5ed680b1
-size 4548221488
+oid sha256:6e6001da2106d4757498752a021df6c2bdc332c650aae4bae6b0c004dcf14933
+size 2200119864

model.safetensors.index.json

@@ -1,639 +0,0 @@
-{
-  "metadata": {
-    "total_size": 4548144832
-  },
-  "weight_map": {
-    "model.language_model.embed_tokens.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.merger.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.fc.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.merger.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.pos_embed.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.patch_embed.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.merger.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.pre_fc_norm_embedding.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.pre_fc_norm_hidden.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.merger.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.0.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.1.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.10.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.11.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.12.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.13.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.14.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.15.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.16.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.17.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.18.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.19.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.2.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.20.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.21.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.22.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.23.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.3.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.4.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.5.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.6.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.7.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.8.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.blocks.9.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.merger.norm.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.merger.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.visual.patch_embed.proj.bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors"
-  }
-}

model_card.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+- conversational
+- llama
+- fine-tuned
+- rax
+- raxcore
+model_type: llama
+---
+
+# Rax 3.5 Chat
+
+**Developed by RaxCore - A leading developer company in Africa and beyond**
+
+## Model Description
+
+Rax 3.5 Chat is an extensively enhanced conversational AI model featuring breakthrough improvements developed by RaxCore. Built upon the Llama architecture with TinyLlama as foundation, this model incorporates proprietary optimization techniques, advanced training methodologies, and cultural context awareness that significantly exceed baseline performance.
+
+## Quick Start
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("rax-3.5-chat")
+model = AutoModelForCausalLM.from_pretrained("rax-3.5-chat")
+
+messages = [
+    {"role": "system", "content": "You are Rax, a helpful AI assistant."},
+    {"role": "user", "content": "Hello!"}
+]
+
+input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256)
+```
+
+## Model Details
+
+- **Architecture**: Enhanced Llama (1.1B parameters with RaxCore optimizations)
+- **Context Length**: 2048 tokens
+- **Development**: Extensively enhanced by RaxCore with proprietary improvements
+- **Base**: TinyLlama foundation with significant RaxCore upgrades
+- **License**: Apache 2.0
+
+## Intended Use
+
+- Conversational AI applications
+- Research and educational purposes
+- Creative writing assistance
+- Chatbot development
+
+## Limitations
+
+- 2048 token context limit
+- May generate biased or incorrect information
+- Requires responsible deployment practices
+
+## Links
+
+- **RaxCore Website**: [www.raxcore.dev](https://www.raxcore.dev/)
+- **Hugging Face Profile**: [raxcore-dev](https://huggingface.co/raxcore-dev)

preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 16777216,
-        "shortest_edge": 65536
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "image_processor_type": "Qwen2VLImageProcessorFast"
-}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_rax.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""
+Test script for Rax 3.5 Chat model
+"""
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+def test_rax_chat():
+    print("Loading Rax 3.5 Chat model...")
+    
+    # Load model and tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(".")
+    model = AutoModelForCausalLM.from_pretrained(
+        ".",
+        torch_dtype=torch.bfloat16,
+        device_map="auto"
+    )
+    
+    print("Model loaded successfully!")
+    
+    # Test conversation
+    messages = [
+        {"role": "system", "content": "You are Rax, a helpful AI assistant."},
+        {"role": "user", "content": "Hello! Can you tell me about yourself?"}
+    ]
+    
+    # Apply chat template
+    input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    print(f"Input: {input_text}")
+    
+    inputs = tokenizer(input_text, return_tensors="pt")
+    
+    # Generate response
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=128,
+            temperature=0.7,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
+    print(f"Rax: {response}")
+
+if __name__ == "__main__":
+    test_rax_chat()

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,305 +1,41 @@
 {
-    "add_prefix_space": false,
-    "added_tokens_decoder": {
-        "248044": {
-            "content": "<|endoftext|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248045": {
-            "content": "<|im_start|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248046": {
-            "content": "<|im_end|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248047": {
-            "content": "<|object_ref_start|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248048": {
-            "content": "<|object_ref_end|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248049": {
-            "content": "<|box_start|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248050": {
-            "content": "<|box_end|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248051": {
-            "content": "<|quad_start|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248052": {
-            "content": "<|quad_end|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248053": {
-            "content": "<|vision_start|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248054": {
-            "content": "<|vision_end|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248055": {
-            "content": "<|vision_pad|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248056": {
-            "content": "<|image_pad|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248057": {
-            "content": "<|video_pad|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248058": {
-            "content": "<tool_call>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248059": {
-            "content": "</tool_call>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248060": {
-            "content": "<|fim_prefix|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248061": {
-            "content": "<|fim_middle|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248062": {
-            "content": "<|fim_suffix|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248063": {
-            "content": "<|fim_pad|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248064": {
-            "content": "<|repo_name|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248065": {
-            "content": "<|file_sep|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248066": {
-            "content": "<tool_response>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248067": {
-            "content": "</tool_response>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248068": {
-            "content": "<think>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248069": {
-            "content": "</think>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": false
-        },
-        "248070": {
-            "content": "<|audio_start|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248071": {
-            "content": "<|audio_end|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248072": {
-            "content": "<tts_pad>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248073": {
-            "content": "<tts_text_bos>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248074": {
-            "content": "<tts_text_eod>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248075": {
-            "content": "<tts_text_bos_single>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        },
-        "248076": {
-            "content": "<|audio_pad|>",
-            "lstrip": false,
-            "normalized": false,
-            "rstrip": false,
-            "single_word": false,
-            "special": true
-        }
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     },
-    "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,
-    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is true %}\n        {{- '<think>\\n' }}\n    {%- else %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
-    "clean_up_tokenization_spaces": false,
-    "eos_token": "<|im_end|>",
-    "errors": "replace",
-    "model_max_length": 262144,
-    "pad_token": "<|endoftext|>",
-    "split_special_tokens": false,
-    "tokenizer_class": "Qwen2Tokenizer",
-    "unk_token": null,
-    "add_bos_token": false,
-    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-    "extra_special_tokens": {
-        "audio_bos_token": "<|audio_start|>",
-        "audio_eos_token": "<|audio_end|>",
-        "audio_token": "<|audio_pad|>",
-        "image_token": "<|image_pad|>",
-        "video_token": "<|video_pad|>",
-        "vision_bos_token": "<|vision_start|>",
-        "vision_eos_token": "<|vision_end|>"
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
-}
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "name_or_path": "rax-3.5-chat",
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

video_preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 25165824,
-        "shortest_edge": 4096
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "video_processor_type": "Qwen3VLVideoProcessor"
-}