Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,9 @@ saved_model/**/* 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
+datasets/cybersecurity_chinese_mixed_v2.jsonl filter=lfs diff=lfs merge=lfs -text
+datasets/cybersecurity_sharegpt_chinese.jsonl filter=lfs diff=lfs merge=lfs -text
+datasets/pentesting_explanations.jsonl filter=lfs diff=lfs merge=lfs -text
+datasets/securecode_aiml.jsonl filter=lfs diff=lfs merge=lfs -text
+datasets/trendyol_cybersecurity.jsonl filter=lfs diff=lfs merge=lfs -text
+datasets/vulnerability_cnvd.jsonl filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -1,202 +1,202 @@
-
-                                 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
+
+                                 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

@@ -1,24 +1,24 @@
 ---
 library_name: transformers
 license: apache-2.0
-license_link: https://huggingface.co/Qwen/Qwen3.5-0.8B-Base/blob/main/LICENSE
+license_link: https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/LICENSE
 pipeline_tag: image-text-to-text
+base_model:
+- Qwen/Qwen3.5-0.8B-Base
 ---
 
-# Qwen3.5-0.8B-Base
+# Qwen3.5-0.8B
 
 <img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/logo_qwen3.5.png">
 
 [![Qwen Chat](https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5)](https://chat.qwen.ai)
 
 > [!Note]
-> This repository contains model weights and configuration files for the pre-trained only model in the Hugging Face Transformers format. 
-> 
-> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.
-> 
-> The intended use cases are fine-tuning, in-context learning experiments, and other research or development purposes, not direct interaction.
-> However, the control tokens, e.g., `<|im_start|>` and `<|im_end|>` were trained to allow efficient LoRA-style PEFT with the official chat template, mitigating the need to finetune embeddings, a significant optimization given Qwen3.5's larger vocabulary.
-
+> 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.
 
 Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 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.
 
@@ -36,7 +36,6 @@ Qwen3.5 features the following enhancement:
 
 - **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 [Qwen3.5](https://qwen.ai/blog?id=qwen3.5).
 
 
@@ -61,7 +60,900 @@ For more details, please refer to our blog post [Qwen3.5](https://qwen.ai/blog?i
         - Intermediate Dimension: 3584
     - LM Output: 248320 (Tied to token embedding)
     - MTP: trained with multi-steps  
-- Context Length: 262,144 natively and extensible up to 1,010,000 tokens.
+- 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;">Qwen3-4B-2507</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3-1.7B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.5-2B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.5-0.8B</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)">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;">Qwen3-VL-4B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3-VL-2B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.5-2B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.5-0.8B</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)">1.0/0.0</td>
+<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.0/0.0</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 Qwen3.5 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 sampling configuration but with temperature=0.6 under the thinking mode. Under the non-thinking mode, the sampling parameters 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]
+> Qwen3.5 models support both non-thinking and thinking mode. **Qwen3.5-0.8B operates in non-thinking mode by default**.
+> To enable thinking, refer to the examples [here](#thinking-mode). 
+
+For streamlined integration, we recommend using Qwen3.5 via APIs. Below is a guide to use Qwen3.5 via OpenAI-compatible API. 
+
+### Serving Qwen3.5
+
+Qwen3.5 can be served via APIs with popular inference frameworks.
+In the following, we show example commands to launch OpenAI-Compatible API servers for Qwen3.5 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 Qwen3.5, 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 Qwen/Qwen3.5-0.8B --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 Qwen/Qwen3.5-0.8B --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 Qwen/Qwen3.5-0.8B --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 Qwen3.5, 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 Qwen3.5 usage guide, see the [vLLM Qwen3.5 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 Qwen/Qwen3.5-0.8B --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 Qwen/Qwen3.5-0.8B --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 Qwen/Qwen3.5-0.8B --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 Qwen/Qwen3.5-0.8B --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 Qwen3.5 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 Qwen3.5:
+```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 Qwen/Qwen3.5-0.8B --port 8000 --continuous-batching
+```
+
+### Using Qwen3.5 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
+
+```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="Qwen/Qwen3.5-0.8B",
+    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)
+```
+
+#### Image Input
+
+```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="Qwen/Qwen3.5-0.8B",
+    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)
+```
+
+#### 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."
+            }
+        ]
+    }
+]
+
+# 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="Qwen/Qwen3.5-0.8B",
+    messages=messages,
+    max_tokens=32768,
+    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]
+> Qwen3.5 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 Qwen3.5\" backwards"},
+]
+
+chat_response = client.chat.completions.create(
+    model="Qwen/Qwen3.5-0.8B",
+    messages=messages,
+    max_tokens=81920,
+    temperature=1.0,
+    top_p=0.95,
+    presence_penalty=1.5,
+    extra_body={
+        "top_k": 20,
+        "enable_thinking": True,
+    }, 
+)
+print("Chat response:", chat_response)
+```
+
+> [!Important]
+> In thinking mode, we have observed that when using the recommended sampling parameters, Qwen3.5-0.8B is more prone to entering thinking loops compared to other Qwen3.5 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
+
+Qwen3.5 excels in tool calling capabilities.
+
+### Qwen-Agent
+
+We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to quickly build Agent applications with Qwen3.5. 
+
+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': 'Qwen/Qwen3.5-0.8B',
+    '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/).
+
+## 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.
+
+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"`."
+
+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.
+
+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}
+    ```
+
+    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).
+
 
 ### Citation
 
@@ -75,4 +967,4 @@ If you find our work helpful, feel free to give us a cite.
     year   = {2026},
     url    = {https://qwen.ai/blog?id=qwen3.5}
 }
-```
+```

config.json

@@ -1,75 +1,96 @@
 {
-  "architectures": [
-    "Qwen3_5ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_output_gate": true,
-  "bos_token_id": null,
-  "dtype": "bfloat16",
-  "eos_token_id": 248044,
-  "full_attention_interval": 4,
-  "head_dim": 256,
-  "hidden_act": "silu",
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 3584,
-  "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,
-  "mamba_ssm_dtype": "float32",
-  "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,
-  "pad_token_id": null,
-  "partial_rotary_factor": 0.25,
-  "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "mrope_interleaved": true,
-    "mrope_section": [
-      11,
-      11,
-      10
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
     ],
-    "partial_rotary_factor": 0.25,
-    "rope_theta": 10000000,
-    "rope_type": "default"
-  },
-  "tie_word_embeddings": true,
-  "transformers_version": "5.6.0",
-  "use_cache": true,
-  "vocab_size": 248320
-}
+    "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": 1024,
+        "initializer_range": 0.02,
+        "intermediate_size": 3584,
+        "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": 12,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 768,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 3072,
+        "model_type": "qwen3_5",
+        "num_heads": 12,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 1024,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

configs/train.yaml

@@ -1,7 +1,7 @@
 ### Qwen3.5-0.8B-HOS QLoRA 训练配置 (针对 0.8B 小模型优化)
 
 ### 模型配置
-model_name_or_path: lxcxjxhx/Qwen3.5-0.8B-HOS
+model_name_or_path: /home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B
 trust_remote_code: true
 
 ### 训练方法
@@ -10,7 +10,7 @@ do_train: true
 finetuning_type: lora
 
 ### 数据集配置
-dataset: merged_cybersec
+dataset: cybersecurity_sharegpt_chinese
 dataset_dir: datasets
 template: qwen
 cutoff_len: 2048  # 0.8B 模型可以使用更长的序列

datasets/cybersecurity_chinese_mixed_v2.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09db0023d2cf606b324588388ea9df1abe07daef0800eac34c18b322d5f44895
+size 65166760

datasets/cybersecurity_hq.jsonl

@@ -0,0 +1,20 @@
+{"instruction": "什么是SQL注入攻击？请详细解释其原理和防御方法。", "input": "", "output": "SQL注入是一种常见的网络安全漏洞，攻击者通过在应用程序的输入中插入恶意SQL代码来操纵数据库查询。这可能导致未授权的数据访问、数据修改或删除。\n\n原理：\n1. 应用程序直接将用户输入拼接到SQL查询中\n2. 攻击者利用特殊字符闭合原有查询\n3. 注入恶意SQL语句改变查询逻辑\n\n防御措施：\n1. 使用参数化查询（预编译语句）\n2. 输入验证和过滤\n3. 最小权限原则\n4. 使用ORM框架\n5. WAF（Web应用防火墙）"}
+{"instruction": "解释XSS攻击的原理和类型", "input": "", "output": "XSS（跨站脚本）攻击是指攻击者将恶意脚本注入到网页中，当其他用户浏览该页面时，脚本会在用户浏览器中执行。\n\n类型：\n1. 反射型XSS：恶意脚本在URL参数中，服务器将其反射回页面\n2. 存储型XSS：恶意脚本被存储在服务器数据库中\n3. DOM型XSS：客户端JavaScript代码修改DOM时引入\n\n危害：\n- 窃取cookie和会话令牌\n- 执行恶意操作\n- 钓鱼攻击\n\n防御方法：\n1. 输出编码和转义\n2. 内容安全策略(CSP)\n3. HttpOnly cookie标志\n4. 输入验证"}
+{"instruction": "什么是CSRF攻击？如何防御？", "input": "", "output": "CSRF（跨站请求伪造）攻击迫使已认证用户在不知情的情况下执行非预期操作。攻击者利用用户的身份认证状态发起恶意请求。\n\n攻击原理：\n1. 用户登录目标网站\n2. 用户访问恶意网站或链接\n3. 恶意页面自动发起对目标网站的请求\n4. 浏览器自动携带用户的cookie\n\n防御措施：\n1. 使用CSRF令牌（随机生成的token）\n2. 验证Referer和Origin头\n3. 设置SameSite cookie属性\n4. 双重提交cookie\n5. 自定义请求头"}
+{"instruction": "解释什么是零日漏洞", "input": "", "output": "零日漏洞是指软件中尚未被开发者发现或修补的安全缺陷。'零日'指的是开发者有零天时间来修复漏洞，因为攻击者已经知道并可能正在利用它。\n\n特点：\n1. 未知性：开发者尚未发现\n2. 危险性：没有官方补丁可用\n3. 高价值：在黑市上价格昂贵\n\n攻击流程：\n1. 攻击者发现漏洞\n2. 开发exploit（漏洞利用代码）\n3. 在补丁发布前利用漏洞\n4. 漏洞公开后变为'n日漏洞'\n\n防御建议：\n1. 及时更新软件\n2. 使用入侵检测系统\n3. 最小权限原则\n4. 网络分段"}
+{"instruction": "什么是DDoS攻击？有哪些类型？", "input": "", "output": "DDoS（分布式拒绝服务）攻击通过控制大量被感染的计算机同时向目标发送请求，使目标系统资源耗尽而无法提供正常服务。\n\n攻击类型：\n1. 容量耗尽型：\n   - UDP洪水攻击\n   - ICMP洪水攻击\n   - DNS放大攻击\n\n2. 协议型：\n   - SYN洪水攻击\n   - Ping of Death\n   - Smurf攻击\n\n3. 应用层：\n   - HTTP洪水攻击\n   - Slowloris攻击\n   - CC攻击\n\n防御方法：\n1. 流量过滤和速率限制\n2. CDN分发\n3. Anycast网络\n4. 专门的DDoS防护服务\n5. 黑洞路由"}
+{"instruction": "解释加密和解密的区别", "input": "", "output": "加密是将明文转换为密文的过程，使未授权用户无法读取数据内容。解密是加密的逆过程，将密文恢复为明文。\n\n加密算法类型：\n1. 对称加密：\n   - 使用相同密钥加密和解密\n   - 代表：AES、DES、3DES\n   - 优点：速度快\n   - 缺点：密钥分发困难\n\n2. 非对称加密：\n   - 使用公钥加密，私钥解密\n   - 代表：RSA、ECC、DSA\n   - 优点：解决密钥分发问题\n   - 缺点：速度慢\n\n3. 哈希函数：\n   - 单向不可逆\n   - 代表：SHA-256、MD5\n   - 用于密码存储和完整性验证\n\n应用场景：HTTPS、SSL/TLS、数字签名、密码存储"}
+{"instruction": "什么是社会工程学攻击？", "input": "", "output": "社会工程学是利用人性弱点（如信任、恐惧、贪婪）获取敏感信息的攻击方式。攻击者不直接攻击技术系统，而是操纵人员泄露密码、访问权限等。\n\n常见形式：\n1. 钓鱼攻击：\n   - 伪装成可信实体发送邮件\n   - 诱导点击恶意链接\n   - 伪造登录页面\n\n2. 电话诈骗：\n   - 冒充IT支持人员\n   - 索要密码或验证码\n\n3. 尾随进入：\n   - 跟随授权人员进入限制区域\n\n4. 借口攻击：\n   - 编造紧急情况获取信息\n\n防御措施：\n1. 安全意识培训\n2. 多因素认证\n3. 验证身份流程\n4. 最小权限原则"}
+{"instruction": "解释什么是渗透测试", "input": "", "output": "渗透测试是模拟恶意攻击者的技术手段，对系统、网络或应用进行安全评估的过程。目的是发现系统中的安全漏洞并评估其风险。\n\n测试类型：\n1. 黑盒测试：测试者不了解系统信息\n2. 白盒测试：测试者完全了解系统信息\n3. 灰盒测试：部分了解系统信息\n\n测试阶段：\n1. 信息收集：域名、IP、端口、服务\n2. 漏洞扫描：使用工具检测已知漏洞\n3. 漏洞利用：尝试利用发现的漏洞\n4. 权限提升：获取更高权限\n5. 报告编写：记录发现和建议\n\n常用工具：\n- Nmap（端口扫描）\n- Metasploit（漏洞利用）\n- Burp Suite（Web测试）\n- Wireshark（网络分析）"}
+{"instruction": "什么是多因素认证(MFA)？", "input": "", "output": "多因素认证要求用户提供两种或以上的验证方式才能访问系统。基于' something you know, something you have, something you are '原则。\n\n认证因素：\n1. 知识因素（Something you know）：\n   - 密码\n   - PIN码\n   - 安全问题\n\n2. 持有因素（Something you have）：\n   - 手机（短信验证码）\n   - 硬件令牌\n   - 智能卡\n\n3. 生物因素（Something you are）：\n   - 指纹\n   - 人脸识别\n   - 虹膜扫描\n\n优势：\n- 即使密码泄露也能保护账户\n- 显著提高安全性\n- 符合合规要求\n\n实现方式：TOTP、短信验证码、生物识别、硬件密钥"}
+{"instruction": "解释什么是中间人攻击", "input": "", "output": "中间人攻击是指攻击者在通信双方之间拦截并可能篡改信息的攻击方式。攻击者可以窃听通信内容、插入恶意数据或冒充通信双方。\n\n攻击原理：\n1. 攻击者位于通信双方之间\n2. 拦截并可能修改传输的数据\n3. 双方都认为在与对方直接通信\n\n常见场景：\n1. 公共WiFi劫持\n2. ARP欺骗\n3. DNS欺骗\n4. SSL剥离\n\n防御方法：\n1. 使用HTTPS/TLS加密\n2. 证书验证\n3. 端到端加密\n4. VPN\n5. 证书锁定（Certificate Pinning）\n\n检测工具：Wireshark、tcpdump"}
+{"instruction": "什么是安全审计？", "input": "", "output": "安全审计是对信息系统的安全性进行全面检查和评估的过程。包括检查安全策略、访问控制、日志记录、漏洞管理等。\n\n审计内容：\n1. 策略审计：检查安全策略是否完善\n2. 配置审计：检查系统配置是否安全\n3. 日志审计：分析系统日志发现异常\n4. 漏洞审计：扫描系统漏洞\n5. 合规审计：检查是否符合法规要求\n\n审计方法：\n1. 自动化扫描工具\n2. 人工检查\n3. 日志分析\n4. 渗透测试\n\n审计工具：\n- Nessus\n- OpenVAS\n- Qualys\n- Splunk（日志分析）\n\n输出：审计报告，包含发现、风险等级、改进建议"}
+{"instruction": "解释什么是漏洞扫描", "input": "", "output": "漏洞扫描是使用自动化工具检测系统、网络或应用中已知安全漏洞的过程。扫描工具会检查系统配置、软件版本和已知漏洞特征。\n\n扫描类型：\n1. 网络扫描：检测网络设备和服务\n2. 主机扫描：检测操作系统和应用漏洞\n3. Web应用扫描：检测Web漏洞\n4. 数据库扫描：检测数据库配置问题\n\n扫描流程：\n1. 发现目标\n2. 端口和服务识别\n3. 漏洞检测\n4. 风险评估\n5. 生成报告\n\n常见工具：\n- Nessus：企业级漏洞扫描\n- OpenVAS：开源漏洞扫描\n- Qualys：云漏洞管理\n- Burp Suite：Web应用扫描\n- Nmap：网络发现和安全审计\n\n局限性：\n- 只能检测已知漏洞\n- 可能产生误报\n- 无法检测逻辑漏洞"}
+{"instruction": "什么是安全补丁管理？", "input": "", "output": "安全补丁管理是识别、获取、测试和安装软件更新（补丁）以修复安全漏洞的过程。良好的补丁管理是维护系统安全的重要措施。\n\n管理流程：\n1. 漏洞监控：跟踪新发现的安全漏洞\n2. 补丁评估：评估补丁的紧急性和影响\n3. 补丁测试：在测试环境验证补丁\n4. 分批部署：按优先级逐步部署\n5. 验证确认：确认补丁生效且无副作用\n\n最佳实践：\n1. 建立补丁管理策略\n2. 维护资产清单\n3. 自动化补丁部署\n4. 定期审计补丁状态\n5. 保留回滚能力\n\n挑战：\n- 补丁可能引入新问题\n- 关键系统不能随意重启\n- 第三方软件补丁管理\n- 补丁兼容性测试\n\n工具：WSUS、SCCM、Ansible、Chef"}
+{"instruction": "解释什么是蜜罐技术", "input": "", "output": "蜜罐是一种主动防御技术，通过设置诱饵系统吸引攻击者。蜜罐可以收集攻击者的行为信息、攻击工具和攻击方法，帮助安全团队了解威胁态势。\n\n蜜罐类型：\n1. 低交互蜜罐：\n   - 模拟有限服务\n   - 实现简单\n   - 风险较低\n   - 代表：Honeyd\n\n2. 高交互蜜罐：\n   - 真实操作系统\n   - 记录详细行为\n   - 风险较高\n   - 代表：Cowrie、Dionaea\n\n3. 研究蜜罐：\n   - 用于研究攻击行为\n   - 收集恶意软件样本\n\n优势：\n- 早期预警系统\n- 收集攻击情报\n- 分散攻击者注意力\n- 研究攻击趋势\n\n部署注意：\n- 隔离网络环境\n- 监控蜜罐状态\n- 定期分析数据"}
+{"instruction": "什么是数据脱敏？", "input": "", "output": "数据脱敏是对敏感数据进行处理，使其在保持数据格式和特征的��时隐藏真实内容的技术。常用于测试环境、开发环境和数据分析场景。\n\n脱敏方法：\n1. 替换：用假数据替换真实数据\n2. 掩码：隐藏部分字符（如身份证号）\n3. 加密：加密敏感字段\n4. 泛化：降低数据精度（如年龄改为年龄段）\n5. 随机化：随机生成符合格式的数据\n6. 删除：移除敏感字段\n\n应用场景：\n- 测试环境数据准备\n- 开发环境数据使用\n- 数据分析外包\n- 日志文件处理\n- 培训数据准备\n\n脱敏原则：\n1. 保持数据格式\n2. 保持数据关系\n3. 不可逆推\n4. 符合合规要求\n\n工具：Informatica、IBM Optim、Delphix"}
+{"instruction": "解释什么是安全信息和事件管理(SIEM)", "input": "", "output": "SIEM是一种安全解决方案，结合安全信息管理和安全事件管理功能。它实时收集、分析和关联来自各种安全设备、服务器和应用的日志数据，帮助检测安全事件、进行事件响应和合规报告。\n\n核心功能：\n1. 日志收集：集中收集各类安全日志\n2. 事件关联：关联不同来源的事件\n3. 实时告警：检测异常行为并告警\n4. 取证分析：支持安全事件调查\n5. 合规报告：生成合规性报告\n\n数据来源：\n- 防火墙日志\n- IDS/IPS日志\n- 服务器日志\n- 应用日志\n- 数据库日志\n\n优势：\n- 集中化安全管理\n- 实时威胁检测\n- 快速事件响应\n- 满足合规要求\n\n产品：Splunk、QRadar、ArcSight、LogRhythm"}
+{"instruction": "什么是零信任安全模型？", "input": "", "output": "零信任是一种安全理念，核心原则是'永不信任，始终验证'。它假设网络内外都存在威胁，不基于网络位置自动信任任何用户或设备。\n\n核心原则：\n1. 始终验证：每次访问都需要验证\n2. 最小权限：只授予必要的权限\n3. 假设入侵：假设网络已被入侵\n4. 持续验证：持续监控和验证\n\n实施要素：\n1. 身份认证：多因素认证\n2. 设备信任：设备健康检查\n3. 微分段：网络细粒度分段\n4. 最小权限访问：基于角色的访问控制\n5. 持续监控：实时监控异常行为\n\n与传统模型对比：\n- 传统：城堡护城河模型，内部可信\n- 零信任：每个访问都要验证\n\n实施挑战：\n- 复杂度高\n- 性能影响\n- 用户体验\n- 实施成本\n\n框架：Google BeyondCorp、Forrester Zero Trust"}
+{"instruction": "解释什么是安全开发生命周期(SDLC)", "input": "", "output": "安全开发生命周期是将安全实践整合到软件开发全过程的方法论。确保在软件开发的每个阶段都考虑安全因素。\n\nSDLC阶段：\n1. 需求分析：\n   - 定义安全需求\n   - 识别合规要求\n   - 威胁建模\n\n2. 设计：\n   - 安全架构设计\n   - 攻击面分析\n   - 安全设计模式\n\n3. 编码：\n   - 安全编码规范\n   - 代码审查\n   - 静态代码分析\n\n4. 测试：\n   - 安全测试\n   - 渗透测试\n   - 漏洞扫描\n\n5. 部署：\n   - 安全配置\n   - 加固措施\n\n6. 维护：\n   - 漏洞管理\n   - 补丁更新\n   - 安全监控\n\n优势：\n- 早期发现安全问题\n- 降低修复成本\n- 提高软件安全性\n- 满足合规要求"}
+{"instruction": "什么是网络隔离？", "input": "", "output": "网络隔离是将网络划分为多个安全区域，通过访问控制策略限制区域间通信的安全措施。目的是限制攻击者在网络中的横向移动，降低安全事件的影响范围。\n\n隔离类型：\n1. 物理隔离：\n   - 完全独立的网络\n   - 最高安全性\n   - 成本较高\n\n2. 逻辑隔离：\n   - VLAN（虚拟局域网）\n   - 防火墙分区\n   - VPN\n\n网络分区：\n1. DMZ（非军事区）：对外服务区\n2. 内部网络：核心业务区\n3. 管理网络：设备管理区\n4. 访客网络：访客上网区\n\n实现技术：\n- VLAN\n- 防火墙\n- ACL（访问控制列表）\n- 网络分段\n- SDN（软件定义网络）\n\n优势：\n- 限制攻击扩散\n- 控制访问权限\n- 提高性能\n- 简化管理"}
+{"instruction": "解释什么是数据泄露防护(DLP)", "input": "", "output": "DLP是防止敏感数据被未授权访问、使用或泄露的技术和策略组合。它通过内容识别、监控和数据保护机制，确保敏感数据在存储、传输和使用过程中的安全性。\n\n防护场景：\n1. 数据使用中：终端设备上的数据\n2. 数据传输中：网络传输的数据\n3. 数据存储中：静态存储的数据\n\n检测技术：\n1. 内容识别：\n   - 正则表达式匹配\n   - 关键词检测\n   - 数据指纹\n   - 机器学习分类\n\n2. 监控方式：\n   - 网络DLP：监控网络流量\n   - 终端DLP：监控终端行为\n   - 存储DLP：扫描存储数据\n\n响应动作：\n- 告警\n- 阻断\n- 加密\n- 隔离\n- 审计日志\n\n实施步骤：\n1. 数据分类分级\n2. 制定安全策略\n3. 部署DLP工具\n4. 监控和调优\n5. 持续改进\n\n产品：Symantec DLP、McAfee DLP、Digital Guardian"}

datasets/cybersecurity_sharegpt_chinese.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016042f48431c2fd166f64c4bd8bb023cae218b013f2904aa02ac27291ca1c1e
+size 170503560

datasets/dataset_info.json

@@ -8,8 +8,22 @@
       "response": "output"
     }
   },
-  "cybersecurity_sharegpt": {
-    "file_name": "cybersecurity_sharegpt.jsonl",
+  "cybersecurity_sharegpt_chinese": {
+    "file_name": "cybersecurity_sharegpt_chinese.jsonl",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations"
+    }
+  },
+  "cybersecurity_chinese_mixed_v2": {
+    "file_name": "cybersecurity_chinese_mixed_v2.jsonl",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations"
+    }
+  },
+  "trendyol_cybersecurity": {
+    "file_name": "trendyol_cybersecurity.jsonl",
     "formatting": "alpaca",
     "columns": {
       "prompt": "instruction",
@@ -17,22 +31,45 @@
       "response": "output"
     }
   },
-  "cnvd_vulnerability": {
-    "file_name": "cnvd_vulnerability.jsonl",
+  "vulnerability_cnvd": {
+    "file_name": "vulnerability_cnvd.jsonl",
     "formatting": "alpaca",
     "columns": {
-      "prompt": "instruction",
-      "query": "input",
-      "response": "output"
+      "prompt": "description",
+      "query": "title",
+      "response": "severity"
     }
   },
-  "merged_cybersec": {
-    "file_name": "merged_cybersec.jsonl",
+  "vulnerability_mitigation_qa": {
+    "file_name": "vulnerability-mitigation-qa-zh_tw_train.jsonl",
     "formatting": "alpaca",
     "columns": {
       "prompt": "instruction",
       "query": "input",
       "response": "output"
     }
+  },
+  "securecode_aiml": {
+    "file_name": "securecode_aiml.jsonl",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations"
+    }
+  },
+  "pentesting_explanations": {
+    "file_name": "pentesting_explanations.jsonl",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages"
+    }
+  },
+  "foresight_safety_bench": {
+    "file_name": "foresight_safety_bench.jsonl",
+    "formatting": "alpaca",
+    "columns": {
+      "prompt": "goal",
+      "query": "subcategory",
+      "response": "category"
+    }
   }
 }

datasets/pentesting_explanations.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae2c8d1de1f21c5b232b99d4e9ba1ac44c94a41f67eff054f4af1d3884203b6
+size 39262031

datasets/secbench.jsonl

@@ -0,0 +1,5 @@
+{"image":{"bytes":null,"path":"\/home\/s\/.cache\/huggingface\/hub\/datasets--secbench-hf--SecBench\/snapshots\/7ed8fa844f15ba10762b8b676b4616749f42f29a\/figs\/SecBench_design.png"}}
+{"image":{"bytes":null,"path":"\/home\/s\/.cache\/huggingface\/hub\/datasets--secbench-hf--SecBench\/snapshots\/7ed8fa844f15ba10762b8b676b4616749f42f29a\/figs\/benchmarking_MCQ.png"}}
+{"image":{"bytes":null,"path":"\/home\/s\/.cache\/huggingface\/hub\/datasets--secbench-hf--SecBench\/snapshots\/7ed8fa844f15ba10762b8b676b4616749f42f29a\/figs\/benchmarking_SAQ.png"}}
+{"image":{"bytes":null,"path":"\/home\/s\/.cache\/huggingface\/hub\/datasets--secbench-hf--SecBench\/snapshots\/7ed8fa844f15ba10762b8b676b4616749f42f29a\/figs\/example_MCQ.png"}}
+{"image":{"bytes":null,"path":"\/home\/s\/.cache\/huggingface\/hub\/datasets--secbench-hf--SecBench\/snapshots\/7ed8fa844f15ba10762b8b676b4616749f42f29a\/figs\/example_SAQ.png"}}

datasets/securecode_aiml.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0e8e052fc173bf403f99e676d12d4a38567c129c841fa30f0795eba94fc2d1
+size 33242649

datasets/trendyol_cybersecurity.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0944a15192a0ad4f33395809f01be4e23b845999402c8856633fc111f06ec43
+size 194854018

datasets/vulnerability-mitigation-qa-zh_tw_train.jsonl

@@ -0,0 +1,22 @@
+{"messages":"[{\"role\": \"user\", \"content\": \"缺少 CSP header 會對網站安全造成什麼風險？\"}, {\"role\": \"assistant\", \"content\": \"沒有設置 Content Security Policy (CSP) header，網站會更容易受到 Cross-Site Scripting (XSS) 攻擊，因為缺少對資源加載的明確指令。為了減少這個風險，你應該在 Web 伺服器中設置一個強健的 CSP header，指定允許加載的資源類型（腳本、樣式等）及其來源。\"}]","instruction":"","input":"缺少 CSP header 會對網站安全造成什麼風險？","output":"沒有設置 Content Security Policy (CSP) header，網站會更容易受到 Cross-Site Scripting (XSS) 攻擊，因為缺少對資源加載的明確指令。為了減少這個風險，你應該在 Web 伺服器中設置一個強健的 CSP header，指定允許加載的資源類型（腳本、樣式等）及其來源。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"Web 伺服器設置中缺少 X-Frame-Options header 會帶來什麼問題？\"}, {\"role\": \"assistant\", \"content\": \"如果沒有 X-Frame-Options header，網站容易受到 clickjacking 攻擊，攻擊者可能會將該網站嵌入到惡意網站的 iframe 中。為了防止這種情況，應在 Web 伺服器中設置 X-Frame-Options header，將其值設置為 'DENY' 或 'SAMEORIGIN'，具體取決於你的需求。\"}]","instruction":"","input":"Web 伺服器設置中缺少 X-Frame-Options header 會帶來什麼問題？","output":"如果沒有 X-Frame-Options header，網站容易受到 clickjacking 攻擊，攻擊者可能會將該網站嵌入到惡意網站的 iframe 中。為了防止這種情況，應在 Web 伺服器中設置 X-Frame-Options header，將其值設置為 'DENY' 或 'SAMEORIGIN'，具體取決於你的需求。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"為什麼在 Web 伺服器中設置 Secure 標記對 Cookie 很重要？\"}, {\"role\": \"assistant\", \"content\": \"如果 Cookie 沒有設置 Secure 標記，這些 Cookie 可能會通過未加密的 HTTP 連接傳輸，從而容易被攻擊者攔截。為了避免這種風險，應確保所有 Cookie 都設置了 Secure 標記，這樣它們只能通過 HTTPS 連接傳輸。\"}]","instruction":"","input":"為什麼在 Web 伺服器中設置 Secure 標記對 Cookie 很重要？","output":"如果 Cookie 沒有設置 Secure 標記，這些 Cookie 可能會通過未加密的 HTTP 連接傳輸，從而容易被攻擊者攔截。為了避免這種風險，應確保所有 Cookie 都設置了 Secure 標記，這樣它們只能通過 HTTPS 連接傳輸。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"缺少 SameSite 屬性的 Cookie 會帶來什麼風險？\"}, {\"role\": \"assistant\", \"content\": \"如果 Cookie 缺少 SameSite 屬性，這些 Cookie 更容易受到 Cross-Site Request Forgery (CSRF) 攻擊，因為它們允許與第三方網站發送請求。為了降低這種風險，應在 Web 伺服器中將 SameSite 屬性設置為 'Strict' 或 'Lax'，以限制 Cookie 的發送時機。\"}]","instruction":"","input":"缺少 SameSite 屬性的 Cookie 會帶來什麼風險？","output":"如果 Cookie 缺少 SameSite 屬性，這些 Cookie 更容易受到 Cross-Site Request Forgery (CSRF) 攻擊，因為它們允許與第三方網站發送請求。為了降低這種風險，應在 Web 伺服器中將 SameSite 屬性設置為 'Strict' 或 'Lax'，以限制 Cookie 的發送時機。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"Web 伺服器沒有啟用 HTTP Strict Transport Security (HSTS) 會有什麼風險？\"}, {\"role\": \"assistant\", \"content\": \"如果沒有啟用 HSTS，使用者可能通過未加密的 HTTP 訪問網站，這使得他們容易受到中間人攻擊 (MITM)。為了解決這個問題，應在 Web 伺服器中設置 Strict-Transport-Security header，確保瀏覽器始終使用 HTTPS 與網站通信。\"}]","instruction":"","input":"Web 伺服器沒有啟用 HTTP Strict Transport Security (HSTS) 會有什麼風險？","output":"如果沒有啟用 HSTS，使用者可能通過未加密的 HTTP 訪問網站，這使得他們容易受到中間人攻擊 (MITM)。為了解決這個問題，應在 Web 伺服器中設置 Strict-Transport-Security header，確保瀏覽器始終使用 HTTPS 與網站通信。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"Cookie 沒有設置 Secure 標記和 SameSite 屬性會帶來什麼問題？\"}, {\"role\": \"assistant\", \"content\": \"這些問題表明網站的 Cookie 設置不夠安全，缺少 Secure 標記可能使 Cookie 在不安全的 HTTP 連接中被傳輸，缺少 SameSite 屬性可能導致跨站請求偽造 (CSRF) 攻擊。應確保在 Web 伺服器中設置 Cookie 的 Secure 標記以便僅通過 HTTPS 傳輸，同時設置 SameSite 屬性以限制第三方請求。\"}]","instruction":"","input":"Cookie 沒有設置 Secure 標記和 SameSite 屬性會帶來什麼問題？","output":"這些問題表明網站的 Cookie ��置不夠安全，缺少 Secure 標記可能使 Cookie 在不安全的 HTTP 連接中被傳輸，缺少 SameSite 屬性可能導致跨站請求偽造 (CSRF) 攻擊。應確保在 Web 伺服器中設置 Cookie 的 Secure 標記以便僅通過 HTTPS 傳輸，同時設置 SameSite 屬性以限制第三方請求。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"沒有設置 HTTP 嚴格傳輸安全 (HSTS) header 會有什麼風險？\"}, {\"role\": \"assistant\", \"content\": \"沒有 HSTS header，網站容易受到中間人攻擊 (MITM)，即使網站支援 HTTPS，也可能因不強制使用而暴露風險。解決方法是啟用 HSTS，讓 Web 伺服器自動將 HTTP 請求重定向到 HTTPS，確保所有通信都通過加密連接進行。\"}]","instruction":"","input":"沒有設置 HTTP 嚴格傳輸安全 (HSTS) header 會有什麼風險？","output":"沒有 HSTS header，網站容易受到中間人攻擊 (MITM)，即使網站支援 HTTPS，也可能因不強制使用而暴露風險。解決方法是啟用 HSTS，讓 Web 伺服器自動將 HTTP 請求重定向到 HTTPS，確保所有通信都通過加密連接進行。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Nginx 中設置 CSP header？\"}, {\"role\": \"assistant\", \"content\": \"在 Nginx 中，你可以通過 `add_header` 指令來設置 Content Security Policy (CSP) header。例如，將以下內容添加到你的 Nginx 設置檔中，允許特定資源的加載：\\n\\n```nginx\\nadd_header Content-Security-Policy \\\"default-src 'self'; script-src 'self' https:\/\/apis.example.com; style-src 'self';\\\";\\n```這樣可以減少網站受到 XSS 攻擊的風險。\"}]","instruction":"","input":"如何在 Nginx 中設置 CSP header？","output":"在 Nginx 中，你可以通過 `add_header` 指令來設置 Content Security Policy (CSP) header。例如，將以下內容添加到你的 Nginx 設置檔中，允許特定資源的加載：\n\n```nginx\nadd_header Content-Security-Policy \"default-src 'self'; script-src 'self' https:\/\/apis.example.com; style-src 'self';\";\n```這樣可以減少網站受到 XSS 攻擊的風險。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Nginx 中設置 X-Frame-Options header 來防止 clickjacking 攻擊？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 Nginx 設置中使用 `add_header` 指令來設置 X-Frame-Options header。將以下內容添加到 Nginx 設置檔中：\\n\\n```nginx\\nadd_header X-Frame-Options \\\"DENY\\\";\\n```這樣可以阻止網站被嵌入到 iframe 中，有效防止 clickjacking 攻擊。\"}]","instruction":"","input":"如何在 Nginx 中設置 X-Frame-Options header 來防止 clickjacking 攻擊？","output":"你可以在 Nginx 設置中使用 `add_header` 指令來設置 X-Frame-Options header。將以下內容添加到 Nginx 設置檔中：\n\n```nginx\nadd_header X-Frame-Options \"DENY\";\n```這樣可以阻止網站被嵌入到 iframe 中，有效防止 clickjacking 攻擊。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Nginx 中設置 Cookie 的 Secure 標記？\"}, {\"role\": \"assistant\", \"content\": \"在 Nginx 中，可以通過設置 SSL 並將 `Secure` 標記應用到 Set-Cookie header。首先，確保網站已經設置了 SSL，然後可以在 `Set-Cookie` 指令中添加 `Secure` 標記，例如：\\n\\n```nginx\\nproxy_cookie_path \/ \\\"\/; Secure\\\";\\n```這樣，Cookie 就只能通過 HTTPS 傳輸，增強了安全性。\"}]","instruction":"","input":"如何在 Nginx 中設置 Cookie 的 Secure 標記？","output":"在 Nginx 中，可以通過設置 SSL 並將 `Secure` 標記應用到 Set-Cookie header。首先，確保網站已經設置了 SSL，然後可以在 `Set-Cookie` 指令中添加 `Secure` 標記，例如：\n\n```nginx\nproxy_cookie_path \/ \"\/; Secure\";\n```這樣，Cookie 就只能通過 HTTPS 傳輸，增強了安全性。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Nginx 中設置 Cookie 的 SameSite 屬性？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 Nginx 中通過 `proxy_cookie_path` 指令來設置 Cookie 的 SameSite 屬性。以下是設置 SameSite 屬性的示例：\\n\\n```nginx\\nproxy_cookie_path \/ \\\"\/; SameSite=Strict\\\";\\n```這樣可以有效防止跨站請求偽造 (CSRF) 攻擊，限制 Cookie 在第三方網站中的使用。\"}]","instruction":"","input":"如何在 Nginx 中設置 Cookie 的 SameSite 屬性？","output":"你可以在 Nginx 中通過 `proxy_cookie_path` 指令來設置 Cookie 的 SameSite 屬性。以下是設置 SameSite 屬性的示例：\n\n```nginx\nproxy_cookie_path \/ \"\/; SameSite=Strict\";\n```這樣可以有效防止跨站請求偽造 (CSRF) 攻擊，限制 Cookie 在第三方網站中的使用。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Nginx 中啟用 HSTS 來強制使用 HTTPS？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 Nginx 中使用 `add_header` 指令來啟用 HTTP Strict Transport Security (HSTS)。以下是設置範例：\\n\\n```nginx\\nadd_header Strict-Transport-Security \\\"max-age=31536000; includeSubDomains\\\" always;\\n```這樣可以確保所有的 HTTP 請求都被重定向到 HTTPS，並且在未來的請求中強制使用 HTTPS 連接。\"}]","instruction":"","input":"如何在 Nginx 中啟用 HSTS 來強制使用 HTTPS？","output":"你可以在 Nginx 中使用 `add_header` 指令來啟用 HTTP Strict Transport Security (HSTS)。以下是設置範例：\n\n```nginx\nadd_header Strict-Transport-Security \"max-age=31536000; includeSubDomains\" always;\n```這樣可以確保所有的 HTTP 請求都被重定向到 HTTPS，並且在未來的請求中強制使用 HTTPS 連接。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Apache 中設置 CSP header？\"}, {\"role\": \"assistant\", \"content\": \"在 Apache 中，你可以使用 `Header` 指令來設置 Content Security Policy (CSP) header。將以下內容添加到 Apache 設置檔中，允許特定資源的加載：\\n\\n```apache\\n<IfModule mod_headers.c>\\n  Header set Content-Security-Policy \\\"default-src 'self'; script-src 'self' https:\/\/apis.example.com; style-src 'self';\\\"\\n<\/IfModule>\\n```這樣可以減少網站受到 XSS 攻擊的風險。\"}]","instruction":"","input":"如何在 Apache 中設置 CSP header？","output":"在 Apache 中，你可以使用 `Header` 指令來設置 Content Security Policy (CSP) header。將以下內容添加到 Apache 設置檔中，允許特定資源的加載：\n\n```apache\n<IfModule mod_headers.c>\n  Header set Content-Security-Policy \"default-src 'self'; script-src 'self' https:\/\/apis.example.com; style-src 'self';\"\n<\/IfModule>\n```這樣可以減少網站受到 XSS 攻擊的風險。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Apache 中設置 X-Frame-Options header 來防止 clickjacking 攻擊？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 Apache 設置中使用 `Header` 指令來設置 X-Frame-Options header。將以下內容添加到 Apache 設置檔中：\\n\\n```apache\\n<IfModule mod_headers.c>\\n  Header always set X-Frame-Options \\\"DENY\\\"\\n<\/IfModule>\\n```這樣可以阻止網站被嵌入到 iframe 中，有效防止 clickjacking 攻擊。\"}]","instruction":"","input":"如何在 Apache 中設置 X-Frame-Options header 來防止 clickjacking 攻擊？","output":"你可以在 Apache 設置中使用 `Header` 指令來設置 X-Frame-Options header。將以下內容添加到 Apache 設置檔中：\n\n```apache\n<IfModule mod_headers.c>\n  Header always set X-Frame-Options \"DENY\"\n<\/IfModule>\n```這樣可以阻止網站被嵌入到 iframe 中，有效防止 clickjacking 攻擊。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Apache 中設置 Cookie 的 Secure 標記？\"}, {\"role\": \"assistant\", \"content\": \"在 Apache 中，當你使用 HTTPS 設置網站時，可以使用 `Header` 指令來設置 Cookie 的 Secure 標記。確保網站已經啟用了 SSL，然後可以在 Apache 設置中使用以下指令：\\n\\n```apache\\n<IfModule mod_headers.c>\\n  Header edit Set-Cookie ^(.*)$ $1;Secure\\n<\/IfModule>\\n```這樣，Cookie 就只能通過 HTTPS 傳輸，增強了安全性。\"}]","instruction":"","input":"如何在 Apache 中設置 Cookie 的 Secure 標記？","output":"在 Apache 中，當你使用 HTTPS 設置網站時，可以使用 `Header` 指令來設置 Cookie 的 Secure 標記。確保網站已經啟用了 SSL，然後可以在 Apache 設置中使用以下指令：\n\n```apache\n<IfModule mod_headers.c>\n  Header edit Set-Cookie ^(.*)$ $1;Secure\n<\/IfModule>\n```這樣，Cookie 就只能通過 HTTPS 傳輸，增強了安全性。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Apache 中設置 Cookie 的 SameSite 屬性？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 Apache 中使用 `Header` 指令來設置 Cookie 的 SameSite 屬性。以下是設置 SameSite 屬性的示例：\\n\\n```apache\\n<IfModule mod_headers.c>\\n  Header edit Set-Cookie ^(.*)$ $1;SameSite=Strict\\n<\/IfModule>\\n```這樣可以有效防止跨站請求偽造 (CSRF) 攻擊，限制 Cookie 在第三方網站中的使用。\"}]","instruction":"","input":"如何在 Apache 中設置 Cookie 的 SameSite 屬性？","output":"你可以在 Apache 中使用 `Header` 指令來設置 Cookie 的 SameSite 屬性。以下是設置 SameSite 屬性的示例：\n\n```apache\n<IfModule mod_headers.c>\n  Header edit Set-Cookie ^(.*)$ $1;SameSite=Strict\n<\/IfModule>\n```這樣可以有效防止跨站請求偽造 (CSRF) 攻擊，限制 Cookie 在第三方網站中的使用。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 Apache 中啟用 HSTS 來強制使用 HTTPS？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 Apache 中使用 `Header` 指令來啟用 HTTP Strict Transport Security (HSTS)。以下是設置範例：\\n\\n```apache\\n<IfModule mod_headers.c>\\n  Header always set Strict-Transport-Security \\\"max-age=31536000; includeSubDomains\\\"\\n<\/IfModule>\\n```這樣可以確保所有的 HTTP 請求都被重定向到 HTTPS，並且在未來的請求中強制使用 HTTPS 連接。\"}]","instruction":"","input":"如何在 Apache 中啟用 HSTS 來強制使用 HTTPS？","output":"你可以在 Apache 中使用 `Header` 指令來啟用 HTTP Strict Transport Security (HSTS)。以下是設置範例：\n\n```apache\n<IfModule mod_headers.c>\n  Header always set Strict-Transport-Security \"max-age=31536000; includeSubDomains\"\n<\/IfModule>\n```這樣可以確保所有的 HTTP 請求都被重定向到 HTTPS，並且在未來的請求中強制使用 HTTPS 連接。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 .NET 中設置 CSP header？\"}, {\"role\": \"assistant\", \"content\": \"在 .NET 中，你可以使用 `HttpContext.Response.Headers` 來設置 Content Security Policy (CSP) header。以下是設置 CSP header 的範例：\\n\\n```csharp\\napp.Use(async (context, next) => {\\n    context.Response.Headers.Add(\\\"Content-Security-Policy\\\", \\\"default-src 'self'; script-src 'self' https:\/\/apis.example.com; style-src 'self';\\\");\\n    await next();\\n});\\n```這樣可以減少網站受到 XSS 攻擊的風險。\"}]","instruction":"","input":"如何在 .NET 中設置 CSP header？","output":"在 .NET 中，你可以使用 `HttpContext.Response.Headers` 來設置 Content Security Policy (CSP) header。以下是設置 CSP header 的範例：\n\n```csharp\napp.Use(async (context, next) => {\n    context.Response.Headers.Add(\"Content-Security-Policy\", \"default-src 'self'; script-src 'self' https:\/\/apis.example.com; style-src 'self';\");\n    await next();\n});\n```這樣可以減少網站受到 XSS 攻擊的風險。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 .NET 中設置 X-Frame-Options header 來防止 clickjacking 攻擊？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 .NET 中使用 `HttpContext.Response.Headers` 來設置 X-Frame-Options header。以下是設置 X-Frame-Options 的範例：\\n\\n```csharp\\napp.Use(async (context, next) => {\\n    context.Response.Headers.Add(\\\"X-Frame-Options\\\", \\\"DENY\\\");\\n    await next();\\n});\\n```這樣可以防止網站被嵌入到 iframe 中，避免 clickjacking 攻擊。\"}]","instruction":"","input":"如何在 .NET 中設置 X-Frame-Options header 來防止 clickjacking 攻擊？","output":"你可以在 .NET 中使用 `HttpContext.Response.Headers` 來設置 X-Frame-Options header。以下是設置 X-Frame-Options 的範例：\n\n```csharp\napp.Use(async (context, next) => {\n    context.Response.Headers.Add(\"X-Frame-Options\", \"DENY\");\n    await next();\n});\n```這樣可以防止網站被嵌入到 iframe 中，避免 clickjacking 攻擊。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 .NET 中設置 Cookie 的 Secure 標記？\"}, {\"role\": \"assistant\", \"content\": \"在 .NET 中，你可以在設置 Cookie 時指定 `Secure` 標記。以下是設置 Secure 標記的範例：\\n\\n```csharp\\nvar cookieOptions = new CookieOptions\\n{\\n    Secure = true,\\n};\\ncontext.Response.Cookies.Append(\\\"MyCookie\\\", \\\"cookieValue\\\", cookieOptions);\\n```這樣可以確保 Cookie 只通過 HTTPS 傳輸，增強安全性。\"}]","instruction":"","input":"如何在 .NET 中設置 Cookie 的 Secure 標記？","output":"在 .NET 中，你可以在設置 Cookie 時指定 `Secure` 標記。以下是設置 Secure 標記的範例：\n\n```csharp\nvar cookieOptions = new CookieOptions\n{\n    Secure = true,\n};\ncontext.Response.Cookies.Append(\"MyCookie\", \"cookieValue\", cookieOptions);\n```這樣可以確保 Cookie 只通過 HTTPS 傳輸，增強安全性。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 .NET 中設置 Cookie 的 SameSite 屬性？\"}, {\"role\": \"assistant\", \"content\": \"你可以在 .NET 中設置 Cookie 時指定 `SameSite` 屬性。以下是設置 SameSite 屬性的範例：\\n\\n```csharp\\nvar cookieOptions = new CookieOptions\\n{\\n    SameSite = SameSiteMode.Strict,\\n};\\ncontext.Response.Cookies.Append(\\\"MyCookie\\\", \\\"cookieValue\\\", cookieOptions);\\n```這樣可以有效防止跨站請求偽造 (CSRF) 攻擊，限制 Cookie 的使用範圍。\"}]","instruction":"","input":"如何在 .NET 中設置 Cookie 的 SameSite 屬性？","output":"你可以在 .NET 中設置 Cookie 時指定 `SameSite` 屬性。以下是設置 SameSite 屬性的範例：\n\n```csharp\nvar cookieOptions = new CookieOptions\n{\n    SameSite = SameSiteMode.Strict,\n};\ncontext.Response.Cookies.Append(\"MyCookie\", \"cookieValue\", cookieOptions);\n```這樣可以有效防止跨站請求偽造 (CSRF) 攻擊，限制 Cookie 的使用範圍。","category":"web"}
+{"messages":"[{\"role\": \"user\", \"content\": \"如何在 .NET 中啟用 HSTS 來強制使用 HTTPS？\"}, {\"role\": \"assistant\", \"content\": \"在 .NET 中，你可以通過設置 HSTS 來強制使用 HTTPS。以下是設置 HSTS 的範例：\\n\\n```csharp\\napp.UseHsts(hsts => hsts.MaxAge(days: 365).IncludeSubdomains());\\n```這樣可以確保瀏覽器強制使用 HTTPS 來訪問網站，並且未來所有請求都使用加密連接。\"}]","instruction":"","input":"如何在 .NET 中啟用 HSTS 來強制使用 HTTPS？","output":"在 .NET 中，你可以通過設置 HSTS 來強制使用 HTTPS。以下是設置 HSTS 的範例：\n\n```csharp\napp.UseHsts(hsts => hsts.MaxAge(days: 365).IncludeSubdomains());\n```這樣可以確保瀏覽器強制使用 HTTPS 來訪問網站，並且未來所有請求都使用加密連接。","category":"web"}

datasets/vulnerability_cnvd.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7825c596648e4ba43f4e2c4c49f466bb99fc25b601ac9f5f5186219caa4d842d
+size 54607226

merged/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}

merged/config.json

@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "Qwen3_5ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "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,
+  "mamba_ssm_dtype": "float32",
+  "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,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "vocab_size": 248320
+}

merged/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.5.0",
+  "use_cache": true
+}

merged/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8503e51cb22c2f89f525fef0ce1c50e1925364f4bcc75956bd3df6ab0d127ca
+size 1504827608

merged/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

merged/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

model.safetensors-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b1c301231dd422b8860db31311ab2721511346a32cb1e079c4c4e5f1fe4696
+size 1746942600

model.safetensors.index.json

@@ -5,70 +5,31 @@
   "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.0.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.10.linear_attn.in_proj_qkv.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.12.linear_attn.in_proj_qkv.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.13.linear_attn.in_proj_qkv.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.16.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.17.linear_attn.in_proj_qkv.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.18.linear_attn.in_proj_qkv.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.20.linear_attn.in_proj_qkv.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.4.linear_attn.in_proj_qkv.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.1.linear_attn.in_proj_qkv.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.16.linear_attn.in_proj_qkv.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.6.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.9.linear_attn.in_proj_qkv.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.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.language_model.layers.21.linear_attn.in_proj_qkv.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.0.linear_attn.in_proj_qkv.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.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.7.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",
     "mtp.layers.0.self_attn.q_proj.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.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.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.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.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.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.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.10.mlp.down_proj.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.19.mlp.down_proj.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.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.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.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.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.19.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.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",
@@ -78,33 +39,72 @@
     "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.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.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.17.mlp.down_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",
+    "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.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.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.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.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.7.mlp.down_proj.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.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.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.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.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.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.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.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.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.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.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.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.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.visual.merger.linear_fc2.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",
@@ -130,50 +130,50 @@
     "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.language_model.layers.12.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.language_model.layers.11.self_attn.o_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.16.linear_attn.out_proj.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.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.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.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",
+    "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.19.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
+    "mtp.fc.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.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.23.self_attn.o_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.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.21.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.21.linear_attn.in_proj_z.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.5.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.17.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.18.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",
-    "mtp.fc.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.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.out_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.7.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.6.linear_attn.in_proj_z.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.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.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.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.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.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.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",
@@ -200,72 +200,72 @@
     "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.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.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.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.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.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",
+    "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",
     "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.10.linear_attn.conv1d.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.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.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.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.1.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.12.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.22.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.2.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.2.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.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.5.linear_attn.conv1d.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.9.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
@@ -293,59 +293,59 @@
     "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.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.12.post_attention_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.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.14.input_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.layers.16.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.10.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.19.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.2.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.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.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.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.21.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.4.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.22.post_attention_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.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.17.input_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.2.input_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.9.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.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.8.input_layernorm.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",
+    "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",
-    "model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
-    "mtp.layers.0.input_layernorm.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.6.input_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.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.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.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.8.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.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.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.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",
@@ -423,73 +423,73 @@
     "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.12.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.11.self_attn.k_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.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.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.10.linear_attn.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",
+    "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.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.12.linear_attn.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.18.linear_attn.norm.weight": "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.13.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.16.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.21.linear_attn.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.5.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.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.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",
-    "mtp.layers.0.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",
+    "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.20.linear_attn.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.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.4.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.10.linear_attn.A_log": "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.0.linear_attn.norm.weight": "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.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.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.1.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.17.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.2.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.22.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.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.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.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.18.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.5.linear_attn.A_log": "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.22.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.10.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.1.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.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.20.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.16.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.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.2.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.22.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.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.8.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.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.22.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"
   }
 }

output/README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+model_name: output
+tags:
+- generated_from_trainer
+- unsloth
+- trl
+- sft
+licence: license
+---
+
+# Model Card for output
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.10.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

output/checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: /home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

output/checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "/home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1de1ddaf6b94c58501bc43fe11721bdc05c95daeed9938ac1831877b312d12c
+size 25587104

output/checkpoint-100/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}

output/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bea1b99f84db01ab94286be1aaab1ef4d7c73047b4f52b2454681debaf5f94
+size 13206859

output/checkpoint-100/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

output/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e29f92fcbb16bde44ab89f2ee88d58095f2cab968aba73e3b397a297bce6bc9
+size 14645

output/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc15dbaa3e9efe813dddec6cbefd41282f813a33fe35b65991f31bd85978d0a1
+size 1465

output/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

output/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

output/checkpoint-100/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.1285140562248994,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0214190093708166,
+      "grad_norm": 1.242326021194458,
+      "learning_rate": 0.0,
+      "loss": 1.5745701789855957,
+      "step": 1
+    },
+    {
+      "epoch": 0.214190093708166,
+      "grad_norm": 0.6980591416358948,
+      "learning_rate": 0.00012,
+      "loss": 1.5450334548950195,
+      "step": 10
+    },
+    {
+      "epoch": 0.428380187416332,
+      "grad_norm": 0.5725776553153992,
+      "learning_rate": 0.00019365079365079365,
+      "loss": 1.3886022567749023,
+      "step": 20
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 0.5259498953819275,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.2720512390136718,
+      "step": 30
+    },
+    {
+      "epoch": 0.856760374832664,
+      "grad_norm": 0.5230262279510498,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 1.2705347061157226,
+      "step": 40
+    },
+    {
+      "epoch": 1.0642570281124497,
+      "grad_norm": 0.5142666101455688,
+      "learning_rate": 0.00014603174603174603,
+      "loss": 1.2368663787841796,
+      "step": 50
+    },
+    {
+      "epoch": 1.2784471218206157,
+      "grad_norm": 0.5656140446662903,
+      "learning_rate": 0.00013015873015873017,
+      "loss": 1.1335124015808105,
+      "step": 60
+    },
+    {
+      "epoch": 1.4926372155287817,
+      "grad_norm": 0.5747864842414856,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 1.1571903228759766,
+      "step": 70
+    },
+    {
+      "epoch": 1.7068273092369477,
+      "grad_norm": 0.5713452696800232,
+      "learning_rate": 9.841269841269841e-05,
+      "loss": 1.1261761665344239,
+      "step": 80
+    },
+    {
+      "epoch": 1.9210174029451137,
+      "grad_norm": 0.6140064001083374,
+      "learning_rate": 8.253968253968255e-05,
+      "loss": 1.092535400390625,
+      "step": 90
+    },
+    {
+      "epoch": 2.1285140562248994,
+      "grad_norm": 0.6067069172859192,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.083101177215576,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 141,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5893872718970880.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

output/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca45e0b598c804d191264f29661a55433c928c5d77781dc14eb4dc194a6837aa
+size 5777

output/checkpoint-141/README.md

@@ -0,0 +1,210 @@
+---
+base_model: /home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

output/checkpoint-141/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "/home/s/MODEL/ACT-DASESS/models/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

output/checkpoint-141/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92b435c4bbc3eff945a8226fd4de21c1297f6c6f6c328c5dfe0e49fcb28981b
+size 25587104

output/checkpoint-141/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}

output/checkpoint-141/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab748a5497198b7da86e3d480edc7649ace880a3054c75c8bd2b898d2cb29e0
+size 13206859

output/checkpoint-141/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

output/checkpoint-141/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3273243eff03b33393526147234b0f38a406f70abf6cb33756e5abf2ad7a5c26
+size 14645

output/checkpoint-141/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50523f740753ddc256a600c77c2f9f5cb8a13a6a1b7773e59b2ea5223bff9e55
+size 1465

output/checkpoint-141/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

output/checkpoint-141/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

output/checkpoint-141/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0214190093708166,
+      "grad_norm": 1.242326021194458,
+      "learning_rate": 0.0,
+      "loss": 1.5745701789855957,
+      "step": 1
+    },
+    {
+      "epoch": 0.214190093708166,
+      "grad_norm": 0.6980591416358948,
+      "learning_rate": 0.00012,
+      "loss": 1.5450334548950195,
+      "step": 10
+    },
+    {
+      "epoch": 0.428380187416332,
+      "grad_norm": 0.5725776553153992,
+      "learning_rate": 0.00019365079365079365,
+      "loss": 1.3886022567749023,
+      "step": 20
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 0.5259498953819275,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.2720512390136718,
+      "step": 30
+    },
+    {
+      "epoch": 0.856760374832664,
+      "grad_norm": 0.5230262279510498,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 1.2705347061157226,
+      "step": 40
+    },
+    {
+      "epoch": 1.0642570281124497,
+      "grad_norm": 0.5142666101455688,
+      "learning_rate": 0.00014603174603174603,
+      "loss": 1.2368663787841796,
+      "step": 50
+    },
+    {
+      "epoch": 1.2784471218206157,
+      "grad_norm": 0.5656140446662903,
+      "learning_rate": 0.00013015873015873017,
+      "loss": 1.1335124015808105,
+      "step": 60
+    },
+    {
+      "epoch": 1.4926372155287817,
+      "grad_norm": 0.5747864842414856,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 1.1571903228759766,
+      "step": 70
+    },
+    {
+      "epoch": 1.7068273092369477,
+      "grad_norm": 0.5713452696800232,
+      "learning_rate": 9.841269841269841e-05,
+      "loss": 1.1261761665344239,
+      "step": 80
+    },
+    {
+      "epoch": 1.9210174029451137,
+      "grad_norm": 0.6140064001083374,
+      "learning_rate": 8.253968253968255e-05,
+      "loss": 1.092535400390625,
+      "step": 90
+    },
+    {
+      "epoch": 2.1285140562248994,
+      "grad_norm": 0.6067069172859192,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.083101177215576,
+      "step": 100
+    },
+    {
+      "epoch": 2.3427041499330654,
+      "grad_norm": 0.6464428305625916,
+      "learning_rate": 5.0793650793650794e-05,
+      "loss": 1.0298160552978515,
+      "step": 110
+    },
+    {
+      "epoch": 2.5568942436412314,
+      "grad_norm": 0.6417136192321777,
+      "learning_rate": 3.492063492063492e-05,
+      "loss": 1.0646396636962892,
+      "step": 120
+    },
+    {
+      "epoch": 2.7710843373493974,
+      "grad_norm": 0.6333876252174377,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 1.024216079711914,
+      "step": 130
+    },
+    {
+      "epoch": 2.9852744310575634,
+      "grad_norm": 0.6364655494689941,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 1.01895170211792,
+      "step": 140
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 141,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8307024379379712.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

output/checkpoint-141/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca45e0b598c804d191264f29661a55433c928c5d77781dc14eb4dc194a6837aa
+size 5777