Duplicate from Accio-Lab/occamy-1.0

Co-authored-by: bit <rabbitz@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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/occamy.png filter=lfs diff=lfs merge=lfs -text
+assets/occamy-main-results.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.

MD5SUMS.txt

@@ -0,0 +1,20 @@
+3ace02b07573d3d141bb7f0d53a7dd1d  model-00000-of-00013.safetensors
+1c388faed4e87957b8aba95ee541318e  model-00001-of-00013.safetensors
+e57cebbe1db94877bb7323588687f89e  model-00002-of-00013.safetensors
+76c2db3d47bd14df68753a536e147bd2  model-00003-of-00013.safetensors
+c6478fad4fe663c1a97f86bdbe0b0c79  model-00004-of-00013.safetensors
+637785713be9adca319f22fc01e7279d  model-00005-of-00013.safetensors
+1fd06564b076813c6eca7e3cc3e53d0f  model-00006-of-00013.safetensors
+1f04b9800a04ba7acda5af720278fb96  model-00007-of-00013.safetensors
+6d0786e87a79b8473822ab71b9e43b2e  model-00008-of-00013.safetensors
+8f66189bffed12c6db396e64c84a1263  model-00009-of-00013.safetensors
+1c93dc29cd94f0a343395a4fab9f3a97  model-00010-of-00013.safetensors
+468bc183238ae4e4ac63fcabad7c2a04  model-00011-of-00013.safetensors
+9880f5c8426f48d7b4b2bc7aa6ca4dcd  model-00012-of-00013.safetensors
+85a8195cb62eb3c2defeec116e932fd4  model-visual.safetensors
+71907987995f2e795e75ad209c5b0a67  config.json
+ee5cbd04766beddae4f5b656ead81fa5  model.safetensors.index.json
+7bcaedf726a05924595b0302d0dd4dc7  preprocessor_config.json
+0c49ac5889183510aa4a1ad947d302f8  processor_config.json
+9875abe48fcffcda8e3e21bcfad4466d  tokenizer_config.json
+4010c9c068169f29bca5d89c5d8e967c  tokenizer.json

README.md

@@ -0,0 +1,265 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model: Qwen/Qwen3.6-35B-A3B
+tags:
+- agent
+- agentic
+- co-work
+- tool-use
+- long-context
+- mixture-of-experts
+- coding
+---
+
+<div align="center">
+  <picture>
+    <img src="assets/accio.svg" width="34%" alt="Accio">
+  </picture>
+  &nbsp;&nbsp;&nbsp;&nbsp;
+  <picture>
+    <img src="assets/occamy.png" width="13%" alt="Occamy logo">
+  </picture>
+  <h1>Occamy-1.0</h1>
+  <p><strong>Open Pareto-frontier 35B Intelligence for Co-work</strong></p>
+</div>
+
+<hr>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://accio-lab.github.io/occamy/"><img alt="Project Website" src="https://img.shields.io/badge/Website-Occamy--1.0-087F6A"></a>
+  <a href="https://huggingface.co/Accio-Lab/Occamy-1.0"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Model-Occamy--1.0-FFD21E"></a>
+  <a href="https://github.com/Accio-Lab/Dressage"><img alt="Dressage" src="https://img.shields.io/badge/Training-Dressage-087F6A"></a>
+  <a href="https://arxiv.org/pdf/2609.11977"><img alt="Technical Report" src="https://img.shields.io/badge/%F0%9F%93%84%20Report-Occamy--1.0-B31B1B"></a>
+  <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-blue"></a>
+</div>
+
+<p align="center">
+  <a href="https://accio-lab.github.io/occamy/">Project Website</a> &nbsp;|&nbsp;
+  <a href="https://huggingface.co/Accio-Lab/Occamy-1.0">Model Weights</a> &nbsp;|&nbsp;
+  <a href="https://github.com/Accio-Lab/Dressage">Training Framework</a>
+</p>
+
+## Available Checkpoints
+
+| Format | Download |
+|---|---|
+| GGUF (Q4_K_M / Q8_0) | [occamy-1.0-GGUF](https://huggingface.co/Accio-Lab/occamy-1.0-GGUF) |
+| FP8 | [occamy-1.0-FP8](https://huggingface.co/Accio-Lab/occamy-1.0-FP8) |
+| NVFP4 | [occamy-1.0-NVFP4](https://huggingface.co/Accio-Lab/occamy-1.0-NVFP4) |
+| Experimental MTP head | [occamy-1.0-MTP](https://huggingface.co/Accio-Lab/occamy-1.0-MTP) |
+
+See each model card for usage and validation. Community releases also offer smaller [GGUF quantizations](https://huggingface.co/mradermacher/occamy-1.0-i1-GGUF) and [MLX builds for Apple Silicon](https://huggingface.co/leonsarmiento/Occamy-1.0-6bit-XL-mlx).
+
+BF16, FP8 and NVFP4 each passed a nine-case vLLM compatibility check on a single H200, covering text, code, JSON, tool calls and follow-up, and images. NVFP4 used Marlin W4A16. These checks used ordinary decoding; the separate MTP head remains experimental.
+
+## 1. Model Introduction
+
+Occamy-1.0 is a compact agentic model purpose-built for real-world co-work: long-horizon, stateful tasks that require coordinated use of search, code, tools, files, structured APIs, and productivity software. Starting from the post-trained [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) checkpoint, Occamy concentrates further training on reliable execution, persistent state tracking, recovery, and follow-through rather than relearning general capabilities from scratch.
+
+### Key Features
+
+- **Co-work specialization:** Designed for sustained execution across multi-step professional workflows, not isolated question answering.
+- **Compact inference footprint:** A 35B-total, 3B-active Mixture-of-Experts model that keeps long-running agent workloads practical.
+- **Long-horizon continuity:** Designed to keep work coherent across tool calls, delegated runs, and history rewrites such as context compaction.
+- **Broad agentic capability:** Co-work gains are accompanied by strong tool calling, terminal coding, and instruction following.
+- **Execution-grounded training:** Supervised fine-tuning spans general agentic work, long-horizon interaction, software engineering, and tool-call grounding.
+- **Open training stack:** The multi-harness reinforcement-learning infrastructure used to train Occamy is released as [Dressage](https://github.com/Accio-Lab/Dressage).
+
+> [!NOTE]
+> Occamy is optimized for common co-work workloads, not as a replacement for frontier models on every task. Retrieval-heavy and simulated-user tasks still have headroom, and native browser or desktop visual interaction is not part of the current co-work training interface.
+
+## 2. Model Summary
+
+<div align="center">
+<table>
+<tbody>
+<tr><td align="center"><strong>Architecture</strong></td><td align="center">Mixture-of-Experts causal model with vision encoder</td></tr>
+<tr><td align="center"><strong>Total Parameters</strong></td><td align="center">35B</td></tr>
+<tr><td align="center"><strong>Activated Parameters</strong></td><td align="center">3B</td></tr>
+<tr><td align="center"><strong>Number of Layers</strong></td><td align="center">40</td></tr>
+<tr><td align="center"><strong>Number of Experts</strong></td><td align="center">256</td></tr>
+<tr><td align="center"><strong>Activated Experts</strong></td><td align="center">8 routed + 1 shared</td></tr>
+<tr><td align="center"><strong>Base Architecture Context</strong></td><td align="center">262,144 tokens</td></tr>
+<tr><td align="center"><strong>SFT Sequence Length</strong></td><td align="center">131,072 tokens</td></tr>
+<tr><td align="center"><strong>Starting Checkpoint</strong></td><td align="center"><a href="https://huggingface.co/Qwen/Qwen3.6-35B-A3B">Qwen3.6-35B-A3B</a></td></tr>
+<tr><td align="center"><strong>Post-training</strong></td><td align="center">Full-parameter SFT, HDPO, model merging, and SAO</td></tr>
+</tbody>
+</table>
+</div>
+
+Architecture fields follow the starting checkpoint's published model card. Occamy post-trains the language backbone without changing the architecture; the vision encoder and projector are frozen during SFT. The released checkpoint configuration remains the source of truth for serving limits.
+
+## 3. Evaluation Results
+
+<div align="center">
+  <picture>
+    <img src="assets/occamy-main-results.svg" width="100%" alt="Occamy-1.0 results on co-work, tool-use, coding, and business benchmarks">
+  </picture>
+</div>
+
+### Full Evaluation
+
+<table>
+  <thead>
+    <tr>
+      <th rowspan="2" align="left" bgcolor="#EAF6F3">Benchmark</th>
+      <th colspan="6" align="center" bgcolor="#EAF6F3"><font color="#087F6A">35B-A3B Models</font></th>
+      <th colspan="4" align="center" bgcolor="#EAF6F3"><font color="#087F6A">Large-scale Models</font></th>
+    </tr>
+    <tr>
+      <th align="center" bgcolor="#087F6A"><font color="#FFFFFF">Occamy-1.0</font></th>
+      <th align="center">Qwen3.6<br>35B-A3B</th>
+      <th align="center">Agents-A1</th>
+      <th align="center">Nex-N2-mini</th>
+      <th align="center">BigBang-1.0</th>
+      <th align="center">Ornith-1.5</th>
+      <th align="center">GPT-5.6 Sol</th>
+      <th align="center">Qwen3.8-Max</th>
+      <th align="center">DeepSeek V4<br>Pro (0813)</th>
+      <th align="center">GLM-5.2</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr><td colspan="11" bgcolor="#DDF1EC"><font color="#087F6A"><strong>Co-work</strong></font></td></tr>
+    <tr><td>Claw-Eval (average)</td><td align="right"><strong>82.20</strong></td><td align="right">69.50</td><td align="right"><u>69.90</u></td><td align="right">66.60</td><td align="right">63.50</td><td align="right">64.40</td><td align="right"><u>81.80</u></td><td align="right"><strong>83.92</strong></td><td align="right">81.70</td><td align="right">81.60</td></tr>
+    <tr><td>Claw-Eval (Pass³)</td><td align="right"><strong>71.40</strong></td><td align="right"><u>54.80</u></td><td align="right">41.70</td><td align="right">37.00</td><td align="right">40.20</td><td align="right">48.70</td><td align="right">68.90</td><td align="right"><u>73.68</u></td><td align="right"><strong>74.50</strong></td><td align="right">68.30</td></tr>
+    <tr><td>WildClawBench</td><td align="right"><strong>49.16</strong></td><td align="right">40.40</td><td align="right">30.73</td><td align="right">30.31</td><td align="right">32.87</td><td align="right"><u>45.91</u></td><td align="right"><strong>67.20</strong></td><td align="right"><u>54.42</u></td><td align="right">37.30</td><td align="right">52.14</td></tr>
+    <tr><td>CommerceAgentBench</td><td align="right"><u>37.38</u></td><td align="right">19.60</td><td align="right">9.30</td><td align="right">16.80</td><td align="right">30.80</td><td align="right"><strong>37.40</strong></td><td align="right"><strong>49.50</strong></td><td align="right"><u>46.30</u></td><td align="right">43.30</td><td align="right">39.30</td></tr>
+    <tr><td>Business Arena</td><td align="right"><strong>$79,868</strong></td><td align="right">$44,751</td><td align="right">$33,626</td><td align="right">$13,325</td><td align="right">$56,477</td><td align="right"><u>$66,292</u></td><td align="right"><strong>$168,867</strong></td><td align="right"><u>$89,423</u></td><td align="right">$40,804</td><td align="right">$55,742</td></tr>
+    <tr><td>GDPval<sup>†</sup></td><td align="right"><strong>1,128</strong></td><td align="right"><u>1,004</u></td><td align="right">869</td><td align="right">999</td><td align="right">951</td><td align="right">855</td><td align="right"><strong>1,741</strong></td><td align="right"><u>1,640</u></td><td align="right">1,500</td><td align="right">1,452</td></tr>
+    <tr><td>OfficeQA Pro</td><td align="right"><u>48.10</u></td><td align="right">39.10</td><td align="right">23.30</td><td align="right">46.60</td><td align="right">43.60</td><td align="right"><strong>59.40</strong></td><td align="right"><strong>74.40</strong></td><td align="right"><u>69.20</u></td><td align="right">51.20</td><td align="right">66.20</td></tr>
+    <tr><td>τ³-Bench (Banking)</td><td align="right"><strong>37.10</strong></td><td align="right">11.90</td><td align="right">7.20</td><td align="right"><u>25.80</u></td><td align="right">10.30</td><td align="right">21.70</td><td align="right"><u>46.90</u></td><td align="right"><strong>54.60</strong></td><td align="right">44.30</td><td align="right">37.10</td></tr>
+    <tr><td colspan="11" bgcolor="#DDF1EC"><font color="#087F6A"><strong>Tool calling</strong></font></td></tr>
+    <tr><td>AutomationBench (Pass¹)</td><td align="right"><strong>27.60</strong></td><td align="right">7.50</td><td align="right">2.20</td><td align="right">5.70</td><td align="right">14.80</td><td align="right"><u>18.50</u></td><td align="right"><strong>45.50</strong></td><td align="right"><u>43.50</u></td><td align="right">32.00</td><td align="right">28.00</td></tr>
+    <tr><td>AutomationBench (partial)</td><td align="right"><strong>69.10</strong></td><td align="right">39.40</td><td align="right">14.70</td><td align="right">27.90</td><td align="right">47.40</td><td align="right"><u>58.00</u></td><td align="right"><strong>81.20</strong></td><td align="right"><strong>81.20</strong></td><td align="right">59.70</td><td align="right"><u>70.00</u></td></tr>
+    <tr><td>BFCL v4</td><td align="right"><u>65.40</u></td><td align="right">63.19</td><td align="right">57.23</td><td align="right">62.81</td><td align="right">57.86</td><td align="right"><strong>68.51</strong></td><td align="right">64.33</td><td align="right"><strong>73.65</strong></td><td align="right">67.10</td><td align="right"><u>70.33</u></td></tr>
+    <tr><td>VitaBench</td><td align="right"><u>41.75</u></td><td align="right">34.25</td><td align="right">37.00</td><td align="right">26.25</td><td align="right"><strong>46.00</strong></td><td align="right">40.25</td><td align="right">46.75</td><td align="right"><u>52.25</u></td><td align="right"><strong>53.50</strong></td><td align="right">43.75</td></tr>
+    <tr><td colspan="11" bgcolor="#DDF1EC"><font color="#087F6A"><strong>Coding</strong></font></td></tr>
+    <tr><td>Terminal-Bench 2.1</td><td align="right">59.00</td><td align="right">49.50</td><td align="right">41.60</td><td align="right"><u>60.70<sup>*</sup></u></td><td align="right">33.70</td><td align="right"><strong>67.80<sup>*</sup></strong></td><td align="right"><strong>88.80</strong></td><td align="right">81.30<sup>*</sup></td><td align="right"><u>87.90<sup>*</sup></u></td><td align="right">82.70</td></tr>
+    <tr><td colspan="11" bgcolor="#DDF1EC"><font color="#087F6A"><strong>Instruction following</strong></font></td></tr>
+    <tr><td>IFEval</td><td align="right"><u>91.53</u></td><td align="right">86.90</td><td align="right"><strong>91.60</strong></td><td align="right"><strong>91.60</strong></td><td align="right">90.50</td><td align="right">81.80</td><td align="right"><u>95.00</u></td><td align="right"><strong>95.02</strong></td><td align="right">93.74</td><td align="right">93.89</td></tr>
+  </tbody>
+</table>
+
+Within each size group, **bold** denotes the best result and <u>underlining</u> denotes the second-best result. <sup>*</sup> Official model-card or Artificial Analysis result. <sup>†</sup> Reproduced on the public task release.
+
+### Cost-Performance
+
+<div align="center">
+  <picture>
+    <img src="assets/aggregate-cost-performance.png" width="100%" alt="Aggregate inference cost versus normalized performance across four co-work benchmarks">
+  </picture>
+</div>
+
+Across Claw-Eval, WildClawBench, AutomationBench, and GDPval, Occamy-1.0 lies near the low-cost knee of the empirical Pareto frontier. Relative to its Qwen3.6-35B-A3B starting checkpoint, it delivers a large aggregate capability gain with only a modest change in measured per-task inference cost. Benchmark scores are equally weighted after per-benchmark min-max normalization, and costs are macro-averaged per task under the frozen pricing protocol used in the report.
+
+
+## 4. Training Recipe
+
+Occamy uses staged specialization and consolidation:
+
+```text
+Qwen3.6-35B-A3B
+  ├─ Marathon Expert: SFT → HDPO ┐
+  └─ Sprint Expert: SFT          ├─ Uniform merge → SAO → Occamy-1.0
+```
+
+The Marathon Expert learns sustained execution and accuracy-conditioned efficiency, while the Sprint Expert preserves broader agentic capability. A uniform parameter-space merge combines both experts into one checkpoint with no inference-time routing or ensembling, and a final Single-Rollout Asynchronous Optimization (SAO) stage refines the merged policy on a broad co-work mixture.
+
+The deduplicated SFT union across both experts is:
+
+| Data source | Trajectories | Average length | Tokens |
+| --- | ---: | ---: | ---: |
+| General agentic | 5,418 | 37.7K | 204.1M |
+| Long-horizon interactive agents | 923 | 95.8K | 88.4M |
+| Terminal and software engineering | 1,228 | 35.1K | 43.1M |
+| Tool-call grounding | 7,429 | 9.1K | 67.7M |
+| **Overall** | **14,998** | **26.9K** | **403.3M** |
+
+Training tasks are grounded in executable environments with observable state transitions and task-level grading. The open-source [Dressage](https://github.com/Accio-Lab/Dressage) stack provides multi-harness execution, token-exact trajectory capture, sandbox integration, and multi-segment conversion for reinforcement learning.
+
+## 5. Deployment
+
+Occamy-1.0 keeps the Qwen3.6-35B-A3B architecture, so the [upstream deployment recipe](https://huggingface.co/Qwen/Qwen3.6-35B-A3B#deployment) is the reference serving path. The examples below mirror that recipe with eight-way tensor parallelism and its full context length; adjust both to fit your hardware and confirm them against the released Occamy checkpoint configuration.
+
+### SGLang
+
+The upstream model card recommends [SGLang](https://github.com/sgl-project/sglang) 0.5.10 or newer for the Qwen3.6 architecture.
+
+```bash
+python -m sglang.launch_server \
+  --model-path Accio-Lab/Occamy-1.0 \
+  --port 8000 \
+  --tp-size 8 \
+  --mem-fraction-static 0.8 \
+  --context-length 262144 \
+  --reasoning-parser qwen3 \
+  --tool-call-parser qwen3_coder
+```
+
+### vLLM
+
+The upstream model card recommends [vLLM](https://github.com/vllm-project/vllm) 0.19.0 or newer for the Qwen3.6 architecture.
+
+```bash
+vllm serve Accio-Lab/Occamy-1.0 \
+  --port 8000 \
+  --tensor-parallel-size 8 \
+  --max-model-len 262144 \
+  --reasoning-parser qwen3 \
+  --enable-auto-tool-choice \
+  --tool-call-parser qwen3_coder
+```
+
+Both commands expose an OpenAI-compatible endpoint at `http://localhost:8000/v1`.
+
+## 6. Model Usage
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+
+response = client.chat.completions.create(
+    model="Accio-Lab/Occamy-1.0",
+    messages=[
+        {
+            "role": "user",
+            "content": "Inspect this repository, fix the failing test, and explain the change.",
+        }
+    ],
+    max_tokens=32768,
+    temperature=1.0,
+    top_p=0.95,
+    presence_penalty=1.5,
+    extra_body={
+        "top_k": 20,
+        "chat_template_kwargs": {
+            "enable_thinking": True,
+            "preserve_thinking": True,
+        },
+    },
+)
+
+print(response.choices[0].message.content)
+```
+
+For multi-turn agent runs, retain the complete assistant message returned by the server, including reasoning content and tool calls, then append tool results using the standard OpenAI chat-completions schema. This preserves the execution context that Occamy relies on across long workflows.
+
+### Agent Frameworks
+
+Occamy was trained and evaluated across multiple harnesses, including [OpenClaw](https://github.com/openclaw/openclaw), [Hermes Agent](https://github.com/NousResearch/hermes-agent), and Accio Work. It can be integrated with other tool-using agent frameworks through the same OpenAI-compatible API.
+
+---
+
+## 7. License
+
+This repository is released under the [Apache License 2.0](LICENSE). See the Hugging Face model card for the terms that apply to the model weights.
+
+---
+
+## 8. Contact Us
+
+For questions or feedback, please open an [issue](https://github.com/Accio-Lab/occamy/issues).

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 (preserve_thinking is defined and preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}
+                        {{- 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 +1,122 @@
+{
+ "architectures": [
+  "Qwen3_5MoeForConditionalGeneration"
+ ],
+ "dtype": "bfloat16",
+ "hidden_size": 2048,
+ "image_token_id": 248056,
+ "model_type": "qwen3_5_moe",
+ "text_config": {
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": 248044,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "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_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,
+  "model_type": "qwen3_5_moe_text",
+  "moe_intermediate_size": 512,
+  "mtp_num_hidden_layers": 0,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_experts": 256,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "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"
+  },
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 512,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 248320
+ },
+ "tie_word_embeddings": false,
+ "transformers_version": "5.8.1",
+ "video_token_id": 248057,
+ "vision_config": {
+  "deepstack_visual_indexes": [],
+  "depth": 27,
+  "dtype": "bfloat16",
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "in_channels": 3,
+  "initializer_range": 0.02,
+  "intermediate_size": 4304,
+  "model_type": "qwen3_5_moe_vision",
+  "num_heads": 16,
+  "num_position_embeddings": 2304,
+  "out_hidden_size": 2048,
+  "patch_size": 16,
+  "spatial_merge_size": 2,
+  "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 248054,
+ "vision_start_token_id": 248053
+}

model-00000-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dda86eadaad33fc3e9a6a5b8550f63a14ec963e7ecda4d4744d03c74ae6046c
+size 5368957040

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ad539e80ec8f651cb6ee320fc9ba081336ff879a1671bc9419bb93bd9119ff
+size 5368701040

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5fcf0b762c862bcb21fa6d24c24f7b7c03e1a4f912238060461a86eb8464ad1
+size 5368701232

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2981c3938d931fdc055a318f5194e72cd437cad013f9cfdedd60f0cfff7b04f7
+size 5367991592

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a870c84e78a15fceb67001fecad40e1f569fbfa4722e02c3817b82bf788a5fe1
+size 5368703456

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d16494ae00de6e6dfcc20fb5936a45eade6e958ced6f38ba653d18c307afd8d
+size 5369030168

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c961977adab10850168d10036898fba98064ecf24447c39580343a9e436c86f3
+size 5368703544

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c3b7fb040d0bb4a5c58ac63d3e411084fe2378b7cc887cee5f3ca82dd8a293
+size 5368703704

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1f1f200d1f32452f0d6d1f3e9ead5ac3d2ba168bcbf60c55676ce97ef31756
+size 5367992456

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca0191fa13dfe6e5d1a293e2d943630aeadb0f28c7368eebbfab7fb6627522f
+size 5368703424

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947cc869a23305282d84ee30f26279864d670aa2d2d5093a06775418135fb926
+size 5369030168

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706f8a19066e02ca1b0fce119dd731c22fd23a226c7d274074594b526af1abc6
+size 5368703552

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1e16d4e636defcbef8802da292e21b510b315915ff711f9e9489d62cf9b726
+size 4901660488

model-visual.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f730cecc09c40191e62eacf706743b1ce80a4170a761ba6bd157b102bd9f3edf
+size 893179528

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}