Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/arex-logo.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,201 @@
+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 [yyyy] [name of copyright owner]
+
+   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

@@ -0,0 +1,168 @@
+---
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3.5-4B
+language:
+- en
+tags:
+- agent
+- deep-research
+- reasoning
+- tool-use
+- long-context
+- qwen3.5
+- dense
+---
+
+<div align="center">
+  <img src="assets/arex-logo.png" width="40%" alt="AREX" style="display: block; margin: 0 auto -2px;">
+  <div style="margin-bottom: 7px;"><strong>Towards a Recursively Self-Improving Agent for Deep Research</strong></div>
+  <a href="#"><img src="https://img.shields.io/badge/Paper-AREX-B31B1B?style=flat-square&amp;logo=arxiv&amp;logoColor=white" alt="Paper"></a>
+  <a href="https://vectorspacelab.github.io/arex-model/"><img src="https://img.shields.io/badge/Homepage-AREX-24292F?style=flat-square&amp;logo=googlechrome&amp;logoColor=white" alt="Homepage"></a>
+  <a href="https://arex-research.com/"><img src="https://img.shields.io/badge/Live_Demo-AREX-0F766E?style=flat-square&amp;logo=googlechrome&amp;logoColor=white" alt="AREX Demo"></a>
+  <a href="https://huggingface.co/BAAI/AREX-Base"><img src="https://img.shields.io/badge/Model-AREX--Base-FFD21E?style=flat-square&amp;logo=huggingface&amp;logoColor=000" alt="AREX-Base"></a>
+</div>
+
+## Introduction
+
+AREX is a family of deep research agents developed by the Beijing Academy of Artificial Intelligence (BAAI). It is designed for long-horizon tasks in which an agent must search across sources, assemble candidate answers, verify multiple constraints, and revise its research plan when the available evidence is incomplete.
+
+AREX follows a recursive self-improvement framework consisting of an inner research loop and an outer self-improvement loop. The inner loop conducts deep research, while the outer loop evaluates and improves the research process.
+
+This repository contains **AREX-Turbo**, the compact model in the AREX family. It is a dense 4B model built on Qwen3.5-4B and follows the same recursive deep research framework as AREX-Base. AREX-Turbo targets lower-cost research-agent deployment while retaining AREX's core research, verification, and context-management behavior.
+
+- **Architecture:** Dense
+- **Parameters:** 4B
+- **Context length:** 262,144 tokens
+
+**Key Features**
+
+- **Compact research agent:** provides AREX capabilities in a dense 4B model for lower-cost serving and faster iteration.
+- **Recursive self-improvement:** evaluates provisional answers and chooses whether to accept, refine, or restart the research trajectory.
+- **Verification-guided research:** converts unresolved answer constraints into focused follow-up searches.
+- **Autonomous context updates:** retains verified findings, source identifiers, rejected candidates, open constraints, and the next research plan.
+- **Long-horizon tool use:** supports multi-round search, browsing, evidence integration, and answer construction.
+
+**Model Family**
+
+| Model | Backbone | Context | Positioning |
+| --- | --- | ---: | --- |
+| [AREX-Turbo](https://huggingface.co/BAAI/AREX-Turbo) | Qwen3.5-4B | 256K | Compact model for lower-cost research and tool-use settings. |
+| [AREX-Base](https://huggingface.co/BAAI/AREX-Base) | Qwen3.5-122B-A10B | 256K | Higher-capacity model with the strongest overall AREX results. |
+
+## Method
+
+AREX organizes deep research as two interacting loops supported by autonomous context management.
+
+1. **Inner research loop.** The agent searches, reads, integrates evidence, tracks candidates, and produces a provisional answer with supporting evidence and an answer-level confidence score.
+2. **Outer self-improvement loop.** The agent checks the provisional answer against the original constraints. High-confidence answers are accepted. Recoverable trajectories are refined around unresolved claims, while uninformative trajectories can be restarted.
+3. **Autonomous context update.** The model invokes `update_context` to refresh its research state around verified findings, current and rejected candidates, unresolved constraints, source validity, and the next research plan.
+
+This design preserves useful work across iterations and reduces repeated exploration of paths that have already been rejected.
+
+## Evaluation
+
+AREX is evaluated through a unified long-horizon search-agent interface with `search`, `visit`, `update_context`, and `finish` tools. HLE with tools additionally provides a Python tool.
+
+<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:900px;margin:0 auto;padding:16px 0">
+<table style="width:100%;border-collapse:collapse;font-size:13px;white-space:nowrap">
+<thead><tr>
+<th style="padding:10px 10px;text-align:left;font-weight:600;border-bottom:2px solid #0F766E;color:#0F766E">Model</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">Total Params</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">Browse<br>Comp</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">GAIA</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">xbench-<br>2510</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">DeepSearch<br>QA</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">WideSearch-<br>en</th>
+<th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0F766E;color:#0F766E;font-size:14px">HLE&nbsp;w/<br>tools</th>
+</tr></thead>
+<tbody>
+<tr><td colspan="8" style="padding:8px 12px;font-weight:600;color:#0F766E;border-bottom:1px solid rgba(15,118,110,0.2);background:rgba(15,118,110,0.1)">Frontier models</td></tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">GPT-5.4</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">82.7</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">88.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">77.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">52.1*</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Opus-4.6</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">83.7</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">91.3</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">77.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">53.0*</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Gemini-3.1-Pro</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">85.9</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">53.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">93.3</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">66.4</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">51.4*</td>
+</tr>
+<tr><td colspan="8" style="padding:8px 12px;font-weight:600;color:#0F766E;border-bottom:1px solid rgba(15,118,110,0.2);background:rgba(15,118,110,0.1)">Open-source models</td></tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">GLM-5</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">744B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">75.9</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">70.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">69.8</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">50.4</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Kimi-K2.6</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">1T</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">83.2</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">90.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">92.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.8</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">54.0*</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">DeepSeek-V4-Flash</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">284B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">73.2</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">69.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">90.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">76.4</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">45.1</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">DeepSeek-V4-Pro</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">1.6T</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">83.4</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">88.7</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">78.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">48.2</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Tongyi-DeepResearch</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">30B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">43.4</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">70.9</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">55.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">32.9</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Qwen3.5-35B</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">35B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">61.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">50.3</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">68.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">57.1</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">47.4</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Qwen3.5-122B</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">122B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">63.8</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">81.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">60.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">47.5</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Qwen3.5-397B</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">397B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">78.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">83.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">61.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">82.1</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">74.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">48.3</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">MiroThinker-1.7-mini</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">30B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">67.9</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.3</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">57.2</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">67.9</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">36.4</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">MiroThinker-1.7</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">235B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">74.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">82.7</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">62.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">72.1</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">42.9</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">MiroThinker-H1</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">88.2</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">88.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">72.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">47.7</td>
+</tr>
+<tr>
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15)">Quest-35B</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">35B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">64.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">80.8</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">-</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">60.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">37.2</td>
+</tr>
+<tr><td colspan="8" style="padding:8px 12px;font-weight:600;color:#0F766E;border-bottom:1px solid rgba(15,118,110,0.2);background:rgba(15,118,110,0.1)">AREX models</td></tr>
+<tr style="background:rgba(15,118,110,0.04);font-weight:600">
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15);color:#0F766E">AREX-Turbo</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">4B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">70.7</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">81.6</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">57.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">78.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">68.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">40.6</td>
+</tr>
+<tr style="background:rgba(15,118,110,0.04);font-weight:600">
+<td style="padding:7px 10px;padding-left:20px;border-bottom:1px solid rgba(128,128,128,0.15);color:#0F766E">AREX-Base</td>
+<td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">122B</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">82.5</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">85.4</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">71.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">89.9</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">82.0</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">52.4</td>
+</tr>
+</tbody>
+</table>
+<div style="font-size:12px;color:#6b7280;margin-top:8px;line-height:1.5">* Results reported on the full HLE. Unmarked HLE results use the text-only subset.</div>
+</div>
+
+## Inference
+
+See [`inference/README.md`](inference/README.md) for OpenAI-compatible serving and generation examples. The folder also contains the complete, directly formattable system and user prompts used for BrowseComp.
+
+## Intended Use
+
+AREX-Turbo is intended for research-agent applications that require long-horizon information seeking, evidence aggregation, multi-constraint verification, and tool-augmented reasoning under a smaller model footprint. It is suited to settings where serving cost, latency, or iteration speed matter.
+
+## License
+
+AREX-Turbo is released under the [Apache License 2.0](LICENSE).

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 false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "hidden_size": 2560,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "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": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "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_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": 32,
+    "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": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "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,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

configuration.json

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

inference/README.md

@@ -0,0 +1,71 @@
+# AREX-Turbo Inference
+
+This folder provides a minimal one-turn inference example and the complete BrowseComp prompts. It follows the XML tool-call protocol used by the public AREX evaluation code.
+
+## Serve the model
+
+Run the following commands from the model repository root. Recent versions of vLLM, SGLang, or another OpenAI-compatible server with Qwen3.5 support can be used. For a text-only vLLM deployment:
+
+```bash
+vllm serve . \
+  --served-model-name AREX-Turbo \
+  --tensor-parallel-size 1 \
+  --max-model-len 262144 \
+  --reasoning-parser qwen3 \
+  --language-model-only
+```
+
+Adjust the tensor-parallel size and maximum context length for your hardware.
+
+## Run one generation
+
+Install the client:
+
+```bash
+pip install -U openai
+```
+
+Then send a BrowseComp-style question:
+
+```bash
+export AREX_BASE_URL="http://127.0.0.1:8000/v1"
+export AREX_API_KEY="EMPTY"
+export AREX_MODEL="AREX-Turbo"
+
+python inference/inference.py \
+  --question "Your BrowseComp question"
+```
+
+The script returns the model's next action. When it emits an XML `<tool_call>`, execute that tool, append the assistant output to the message history, and add the real tool result as:
+
+```text
+<tool_response>
+actual tool result
+</tool_response>
+```
+
+Continue until the model calls `finish`. The example intentionally leaves tool execution to the caller.
+
+## Use the prompts directly
+
+[`prompts.py`](prompts.py) exports the BrowseComp system and user prompt constants. Tool descriptions are already embedded in the system prompt, so only the question needs formatting:
+
+```python
+from inference.prompts import (
+    BROWSECOMP_SYSTEM_PROMPT,
+    BROWSECOMP_USER_PROMPT,
+)
+
+question = "Your BrowseComp question"
+messages = [
+    {"role": "system", "content": BROWSECOMP_SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": BROWSECOMP_USER_PROMPT.format(question=question),
+    },
+]
+```
+
+`build_messages(question)` is a convenience wrapper for the same formatting.
+
+BrowseComp exposes `search`, `google_scholar`, `visit`, `update_context`, and `finish`.

inference/__init__.py

@@ -0,0 +1 @@
+"""Minimal inference helpers for AREX."""

inference/inference.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""Run one AREX BrowseComp generation through an OpenAI-compatible endpoint."""
+
+from __future__ import annotations
+
+import argparse
+import os
+
+from prompts import build_messages
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--question", required=True)
+    parser.add_argument(
+        "--base-url",
+        default=os.environ.get("AREX_BASE_URL", "http://127.0.0.1:8000/v1"),
+    )
+    parser.add_argument(
+        "--api-key",
+        default=os.environ.get("AREX_API_KEY", "EMPTY"),
+    )
+    parser.add_argument(
+        "--model",
+        default=os.environ.get("AREX_MODEL", "AREX-Turbo"),
+    )
+    parser.add_argument("--max-tokens", type=int, default=8192)
+    return parser.parse_args()
+
+
+def main() -> None:
+    args = parse_args()
+    try:
+        from openai import OpenAI
+    except ImportError as exc:
+        raise SystemExit("Install the client first: pip install -U openai") from exc
+
+    client = OpenAI(
+        base_url=args.base_url.rstrip("/") + "/",
+        api_key=args.api_key,
+        timeout=600.0,
+    )
+    response = client.chat.completions.create(
+        model=args.model,
+        messages=build_messages(args.question),
+        max_tokens=args.max_tokens,
+        temperature=1.0,
+        top_p=0.95,
+        presence_penalty=1.5,
+        extra_body={"top_k": 20},
+    )
+    print(response.choices[0].message.content or "")
+
+
+if __name__ == "__main__":
+    main()

inference/prompts.py

@@ -0,0 +1,357 @@
+"""Directly formattable AREX prompts for BrowseComp.
+
+The prompt text and tool schemas mirror the public AREX evaluation harness.
+The exported system prompt already contains its tool descriptions; callers only
+need to format the user prompt with ``question=...``.
+"""
+
+from __future__ import annotations
+
+import json
+
+
+_SYSTEM_PROMPT_TEMPLATE = """\
+You are a dedicated worker agent. \
+Your primary role is to plan and orchestrate comprehensive, multi-step research to deliver a accurate answer with thorough and well-supported evidences in response to the user's query. \
+You analyze the problem, plan your research plan, carry out concrete research activities, iteratively use tools and deliver detailed findings with evidences, until complete the whole task.
+
+### Research loop (recommended)
+- Start broad enough to map the landscape, then narrow down. Keep a verification list to help your research.
+- Iteratively use tools like `search` and `visit` to find clues and evidences step by step, until finsh the task.
+- For key claims, Do Not rely on snippets: use `visit` to read full pages.
+- If a line of inquiry fails, change your angle and keep going — the answer exists.
+- You MUST include an explicit verification step before finishing.
+- If the verification step do not fully meet the task requirements, do not finish the task, but should continue to expand the search scope or change the mindset to continue your research.
+
+
+### Global Rules (non-negotiable)
+- **Research**: Use available tools to gather information and conduct thorough investigation
+- **Fact-Based:** All information in your final report must be derived from and supported by the sources you have analyzed, and each piece of evidence must cite the relevant `url`.
+- **Persistence**: The question is guaranteed to have a correct answer that has been validated. If evidence is missing, your approach is insufficient — iterate by research with alternative angles and keep going.
+- **Tool integrity**: Never simulate tool outputs. Always call tools.
+
+
+**Critical Rules:**
+- **ALWAYS use the provided tools.** Never simulate tool outputs or pretend to call tools.
+- The question is guaranteed to have a correct answer that can be found through persistent exploration. If your current approach yields insufficient evidence, broaden and try alternative angles, keywords, and sources.
+- Only call ONE tool function at one time.
+- Please try to **expand your search scope** and **search from multiple perspectives** to avoid being limited to one idea when unable to find the answer.
+
+# Tools
+
+You have access to the following functions:
+
+{tool_des}
+
+If you choose to call a function ONLY reply in the following format with NO suffix:
+
+<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call>
+
+<IMPORTANT>
+Reminder:
+- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags
+- Required parameters MUST be specified
+- For structured parameters such as `query` and `evidences`, the parameter content MUST be valid JSON
+- You may provide optional reasoning in natural language BEFORE the tool call, but NOT after.
+- **ALWAYS call tools. Never simulate tool outputs.**
+</IMPORTANT>\
+"""
+
+
+_USER_PROMPT_TEMPLATE = """\
+Question: {question}
+
+
+**Your Workflow**:
+
+**Phase 1: Plan Your Research**
+
+1. Analyze the question and identify key information needs; Resolve ambiguities or contradictions.
+2. Brainstorm search queries and keywords from different angles. Plan what should investigate at the first step.
+3. Create a Verification Checklist. This checklist can start empty and be built up dynamically as your understanding of the problem evolves.
+
+Example:
+
+The user is asking about [topic]. To answer this correctly, I need to identify what specific information is required and what would constitute a complete answer...
+The fisrt step I'll need to search from...
+
+
+Verification checklist:
+  - [ ] Every key claim is supported by evidence from seaching results
+  - [ ] No unresolved contradictions remain
+  - [ ] The final response matches all constraints in the question
+
+
+**Phase 2: Execute search tool**
+
+Example:
+
+<tool_call>
+<function=search>
+<parameter=query>[
+  "first search query",
+  "second complementary search query"
+]</parameter>
+</function>
+</tool_call>
+
+**Phase 3: Execute visit tool**
+
+Example:
+
+<tool_call>
+<function=visit>
+<parameter=url>The URL(s) of the webpage(s) to visit.</parameter>
+<parameter=goal>The goal of the visit for webpage(s).</parameter>
+</function>
+</tool_call>
+
+
+**Phase 4: Iterate**
+- Continue searching and visiting pages step by step until you have comprehensive information
+- Refine your queries based on what you learn
+- Do NOT stop at search snippets: use `visit` for key claims and critical evidences
+- If the current approach is unproductive, change angle/keywords/sources and keep going — the answer exists
+- Only call one tool each step, carefully analyze the tool's response and the next step and then decide the tool call next step. Strive to make tool calls precise and efficient.
+
+
+**Phase 5: Final Answer**
+
+When you have sufficient information, use the `finish` tool:
+
+You MUST Follow:
+1. **Mandatory verification step**:
+- Re-check every critical claim and citation against the gathered evidences.
+- Only proceed to `finish` once your verification checklist is fully satisfied, otherwise adjust the research plan and continue searching.
+- The `evidences` parameter MUST be a JSON array, and each item MUST contain exactly one `evidence` field and one `url` field.
+
+2. The `finish` tool can only be called separately, do not call `finish` and other fucntions at the same time.
+
+
+Example:
+I've gathered **comprehensive evidence** and cross-checked all critical claims. My verification checklist is fully satisfied: every key claim has supporting evidence, all contradictions have been resolved, and the answer matches all constraints in the question. I'm confident I can now provide a complete, accurate answer with proper citations.
+
+<tool_call>
+<function=finish>
+<parameter=answer>Your concise answer</parameter>
+<parameter=evidences>[
+  {{
+    "evidence": "The specific verified fact or data point supporting the answer.",
+    "url": "https://example.com/source-1"
+  }},
+  {{
+    "evidence": "Another verified fact supporting the answer.",
+    "url": "https://example.com/source-2"
+  }}
+]</parameter>
+<parameter=confidence>Your confidence score</parameter>
+</function>
+</tool_call>
+
+
+<CRITICAL>
+- **START with a search tool call**
+- If you need in-depth analysis or reflection on the tool response, output `<think>` block **before** calling the tool, where you can output the thinking content.
+- Do NOT write any text after the tool call.
+- Do NOT provide answers from your own knowledge
+- ALWAYS use the actual tools provided and Do NOT simulate tool outputs
+- The answer exists and has been validated; do not give up. If you're missing evidence, try more exploration.
+</CRITICAL>
+
+Now begin your research by calling the search tool.\
+"""
+
+
+_SEARCH_TOOL = {
+    "type": "function",
+    "function": {
+        "name": "search",
+        "description": "Performs batched web searches: supply an array 'query'; the tool retrieves the top 10 results for each query in one call",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "description": "Array of query strings. Include multiple complementary search queries in a single call.",
+                }
+            },
+            "required": ["query"],
+        },
+    },
+}
+
+_GOOGLE_SCHOLAR_TOOL = {
+    "type": "function",
+    "function": {
+        "name": "google_scholar",
+        "description": "Leverage Google Scholar to retrieve relevant information from academic publications. Accepts multiple queries.",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "array",
+                    "items": {
+                        "type": "string",
+                        "description": "The search query.",
+                    },
+                    "minItems": 1,
+                    "description": "The list of search queries for Google Scholar.",
+                }
+            },
+            "required": ["query"],
+        },
+    },
+}
+
+_VISIT_TOOL = {
+    "type": "function",
+    "function": {
+        "name": "visit",
+        "description": "Visit webpage(s) and return the summary of the content.",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "url": {
+                    "type": ["string", "array"],
+                    "items": {"type": "string"},
+                    "minItems": 1,
+                    "description": "The URL(s) of the webpage(s) to visit. Can be a single URL or an array of URLs.",
+                },
+                "goal": {
+                    "type": "string",
+                    "description": "The goal of the visit for webpage(s).",
+                },
+            },
+        },
+        "required": ["url", "goal"],
+    },
+}
+
+_UPDATE_CONTEXT_TOOL = {
+    "type": "function",
+    "function": {
+        "name": "update_context",
+        "description": """This tool allows you to compress your memory into a new `context` to maintain long-term focus and avoid context window exhaustion.
+**When to use this tool:**
+1. **Context Saturation:** When the conversation history becomes too long, threatening the token limit.
+2. **Loss of Focus:** When the current search trajectory is cluttered with irrelevant data or the reasoning path has become confusing.
+3. **Milestone Reached:** After completing a significant sub-task, to solidify progress before moving to the next phase.
+
+**Strict Standards for new `context`:**
+When calling `update_context`, the `context` parameter string MUST be a high-density, lossless distillation of all the current messages. It must replace the deleted history with actionable intelligence. You must include:
+* **Confirmed Knowledge with Citations:** You MUST retain the `url` for each fact you preserve.** If you lose the `url` now, you will fail the final verification step. Use the format: `[Fact statement] (Verified in: url)`.
+* **Current State & Next Steps:** Where exactly are we in the problem-solving process and a precise plan for the refreshed context.
+You can also include (but not necessary):
+* **Negative Constraints:** Explicitly state what has been tried and FAILED to prevent repetition.
+
+* **Limitation:** The `update_context` function can only be called separately; do not call `update_context` function and other fucntions at the same time. 
+
+**Critical:** You should aim to solve the problem in a single pass if possible. However, if the task requires extended reasoning, apply this tool strategically. Do not overuse it; "over-cleaning" can lead to loss of subtle details. Aim for maximum information density with minimum token usage.
+""",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "context": {
+                    "type": "string",
+                    "description": "a high-density, loss-less distillation of the current state include **Confirmed Knowledge with Citations** and **Current State**.",
+                }
+            },
+            "required": ["context"],
+        },
+    },
+}
+
+_FINISH_TOOL = {
+    "type": "function",
+    "function": {
+        "name": "finish",
+        "description": "Return the final result when you have a definitive answer. This function signals that your research is complete and you're ready to present the final answer to the user.",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "answer": {
+                    "type": "string",
+                    "description": "A succinct, final answer to the user's query",
+                },
+                "evidences": {
+                    "type": "array",
+                    "description": "Array of evidence objects supporting the final answer. Each piece of evidence must cite exactly **one** `url`. If a fact is supported by multiple documents, choose the most authoritative one.",
+                    "items": {
+                        "type": "object",
+                        "properties": {
+                            "evidence": {
+                                "type": "string",
+                                "description": "The specific verified fact or data point (one sentence)",
+                            },
+                            "url": {
+                                "type": "string",
+                                "description": "The source URL of the evidence",
+                            },
+                        },
+                        "required": ["evidence", "url"],
+                    },
+                },
+                "confidence": {
+                    "type": "string",
+                    "description": " Your confidence score between 0% and 100% for your answer",
+                },
+            },
+            "required": ["answer", "evidences", "confidence"],
+        },
+    },
+}
+
+
+BROWSECOMP_TOOLS = (
+    _SEARCH_TOOL,
+    _GOOGLE_SCHOLAR_TOOL,
+    _VISIT_TOOL,
+    _UPDATE_CONTEXT_TOOL,
+    _FINISH_TOOL,
+)
+
+
+def _format_tool_description(tools: tuple[dict, ...]) -> str:
+    body = "<tools>\n"
+    body += "".join(
+        json.dumps(tool, indent=2, ensure_ascii=False) + "\n"
+        for tool in tools
+    )
+    return body + "</tools>\n"
+
+
+BROWSECOMP_SYSTEM_PROMPT = _SYSTEM_PROMPT_TEMPLATE.format(
+    tool_des=_format_tool_description(BROWSECOMP_TOOLS)
+)
+BROWSECOMP_USER_PROMPT = _USER_PROMPT_TEMPLATE
+
+
+def build_messages(question: str) -> list[dict[str, str]]:
+    """Return the initial system/user messages for one BrowseComp agent run."""
+
+    return [
+        {"role": "system", "content": BROWSECOMP_SYSTEM_PROMPT},
+        {
+            "role": "user",
+            "content": BROWSECOMP_USER_PROMPT.format(question=question),
+        },
+    ]
+
+
+__all__ = [
+    "BROWSECOMP_SYSTEM_PROMPT",
+    "BROWSECOMP_USER_PROMPT",
+    "build_messages",
+]

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17f063779e307cceed658af1c107970a76ae65f33e4764ba6354b8363c28c39
+size 4973340248

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d417b0f47d242aa21dc6a6c4c14a62e74c85a1cdf1861a789a0c655268702d
+size 4105280120

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 9078531072
+  },
+  "weight_map": {
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

preprocessor_config.json

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

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "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": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "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"
+  }
+}

tokenizer.json

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

tokenizer_config.json

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

video_preprocessor_config.json

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