Initial public MLX 8bit release

.gitattributes

@@ -33,3 +33,4 @@ 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

CODE-LICENSE.txt

@@ -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.

LICENSE

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

NOTICE

@@ -0,0 +1,8 @@
+APUS-OpenJev-v1-35B-A3B
+
+Base model: Qwen/Qwen3.5-35B-A3B, revision 59d61f3ce65a6d9863b86d2e96597125219dc754.
+Base weights and configuration retain their upstream Apache-2.0 LICENSE.
+The bundled reference-runtime source derives from xDAN-ms-swift-jev (Apache-2.0; see CODE-LICENSE.txt).
+Changes include 20/40-layer MoE dispatch and preservation of checkpoint FP32 state during BF16 loading.
+See runtime-source-provenance.json, merge-provenance.json and release-manifest.json for source identities.
+Authors: gumpcheng (xDAN2099), zhangxu, APUS AI-LAB.

README.md

@@ -0,0 +1,55 @@
+---
+library_name: mlx
+license: apache-2.0
+base_model: apus-ailab/APUS-OpenJev-v1-35B-A3B
+base_model_relation: quantized
+pipeline_tag: text-generation
+language:
+- en
+- zh
+tags:
+- apus-openjev
+- decision-model
+- mlx
+- apple-silicon
+---
+
+# APUS-OpenJev-v1-35B-A3B-MLX-8bit
+
+[English](README.md) | [中文](README.zh-CN.md) · [Source model](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B) · [Collection](https://huggingface.co/collections/apus-ailab/apus-openjev-v1-6ab1ee888eb002fcdd3a2825) · [MLX-4bit](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B-MLX-4bit) · [GGUF / Ollama](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B-GGUF)
+
+MLX weights (8-bit affine, group size 64) of [APUS-OpenJev-v1-35B-A3B](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B) for **Apple Silicon Macs** (mlx-lm, LM Studio).
+
+OpenJev is a **decision model**: each request supplies a state, an instruction and 2–16 candidates, and the model scores candidate labels A–P. It is not a chat model.
+
+## Quick start
+
+```bash
+pip install mlx-lm
+hf download apus-ailab/APUS-OpenJev-v1-35B-A3B-MLX-8bit --local-dir ./openjev
+python ./openjev/examples/openjev_mlx.py --model ./openjev
+```
+
+`examples/openjev_mlx.py` renders prompts with [openjev_contracts.py](openjev_contracts.py) (the training contract) and returns the exact candidate distribution.
+
+## Parity
+
+Frozen80 with identical prompt tokens, compared with the HF BF16 release (full depth, **71/80 · 88.75%**):
+
+| Run / 运行 | Backend / 后端 | Frozen80 | = HF BF16 | Max Δp |
+|---|---|---:|---:|---:|
+| NVIDIA RTX PRO 6000 (CUDA) | mlx 0.32.2 on Linux x86_64 (Device(gpu, 0)) | 71/80 · 88.75% | 80/80 | 0.1931 |
+
+Converted and scored with MLX on Linux (CUDA); the files are platform-independent and load unchanged on Apple Silicon (for 4B, the same kind of file gave identical decisions on CUDA and Metal). Peak memory on Frozen80 was 38.66 GB; plan for a Mac with at least 64 GB of unified memory. Frozen80 is a reused development panel, not a blind benchmark.
+
+## Conversion
+
+- mlx-lm `0.31.3` / mlx `0.32.2`; 8-bit affine, group size 64.
+- GDN `A_log` and `linear_attn.norm.weight` keep their source precision (FP32 in the 35B release).
+- Full depth only, text only, probabilities **not calibrated**.
+
+## License
+
+Apache-2.0, inherited from the source model; see [LICENSE](LICENSE). Base model: [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B).
+
+**Authors:** gumpcheng ([xDAN2099](https://huggingface.co/xDAN2099)), zhangxu, [APUS AI-LAB](https://github.com/APUS-AI-Lab).

README.zh-CN.md

@@ -0,0 +1,55 @@
+---
+library_name: mlx
+license: apache-2.0
+base_model: apus-ailab/APUS-OpenJev-v1-35B-A3B
+base_model_relation: quantized
+pipeline_tag: text-generation
+language:
+- en
+- zh
+tags:
+- apus-openjev
+- decision-model
+- mlx
+- apple-silicon
+---
+
+# APUS-OpenJev-v1-35B-A3B-MLX-8bit
+
+[English](README.md) | [中文](README.zh-CN.md) · [源模型](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B) · [Collection](https://huggingface.co/collections/apus-ailab/apus-openjev-v1-6ab1ee888eb002fcdd3a2825) · [MLX-4bit](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B-MLX-4bit) · [GGUF / Ollama](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B-GGUF)
+
+[APUS-OpenJev-v1-35B-A3B](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-35B-A3B) 的 MLX 权重（8bit affine，group size 64），适用于 **Apple Silicon Mac**（mlx-lm、LM Studio）。
+
+OpenJev 是**决策模型**：每个请求给出状态、指令和 2–16 个候选，模型对候选标签 A–P 打分。它不是聊天模型。
+
+## 快速开始
+
+```bash
+pip install mlx-lm
+hf download apus-ailab/APUS-OpenJev-v1-35B-A3B-MLX-8bit --local-dir ./openjev
+python ./openjev/examples/openjev_mlx.py --model ./openjev
+```
+
+`examples/openjev_mlx.py` 使用 [openjev_contracts.py](openjev_contracts.py)（训练时的格式）渲染 prompt，返回精确的候选分布。
+
+## 一致性
+
+Frozen80 使用完全相同的 prompt token，与 HF BF16 发布版（完整深度，**71/80 · 88.75%**）对比：
+
+| Run / 运行 | Backend / 后端 | Frozen80 | = HF BF16 | Max Δp |
+|---|---|---:|---:|---:|
+| NVIDIA RTX PRO 6000 (CUDA) | mlx 0.32.2 on Linux x86_64 (Device(gpu, 0)) | 71/80 · 88.75% | 80/80 | 0.1931 |
+
+在 Linux（CUDA）上用 MLX 转换并评测；MLX 文件与平台无关，可直接在 Apple Silicon 上加载（4B 的同类文件在 CUDA 与 Metal 上决策完全一致）。Frozen80 评测峰值内存 38.66 GB，建议使用统一内存不少于 64 GB 的 Mac。Frozen80 是复用的开发面板，不是盲测。
+
+## 转换说明
+
+- mlx-lm `0.31.3` / mlx `0.32.2`；8bit affine，group size 64。
+- GDN 的 `A_log` 和 `linear_attn.norm.weight` 保持源精度（35B 发布版中为 FP32）。
+- 仅完整深度、仅文本，概率**未经校准**。
+
+## 许可
+
+Apache-2.0，继承自源模型，见 [LICENSE](LICENSE)。基座模型：[Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B)。
+
+**作者：** gumpcheng（[xDAN2099](https://huggingface.co/xDAN2099)）、zhangxu、[APUS AI-LAB](https://github.com/APUS-AI-Lab)。

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 +1,753 @@
+{
+    "architectures": [
+        "Qwen3_5MoeForConditionalGeneration"
+    ],
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5_moe",
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2048,
+        "initializer_range": 0.02,
+        "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,
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_moe_text",
+        "moe_intermediate_size": 512,
+        "mtp_num_hidden_layers": 1,
+        "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,
+        "rms_norm_eps": 1e-06,
+        "router_aux_loss_coef": 0.001,
+        "shared_expert_intermediate_size": 512,
+        "use_cache": true,
+        "vocab_size": 248320,
+        "mamba_ssm_dtype": "float32",
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "rope_theta": 10000000,
+            "partial_rotary_factor": 0.25,
+            "type": "default"
+        }
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.0.dev0",
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

conversion-provenance.json

@@ -0,0 +1,23 @@
+{
+  "llama_cpp": {
+    "tag": "b11118",
+    "commit": "e6ab7c1a41054a888ada952eab4c886444c2f5ad"
+  },
+  "ollama": "0.34.3",
+  "mlx": "0.32.2",
+  "mlx_lm": "0.31.3",
+  "convert_env": {
+    "torch": "2.11.0+cpu",
+    "transformers": "4.57.6"
+  },
+  "reference_runtime": {
+    "torch": "2.8.0+cu128",
+    "transformers": "5.16.1",
+    "effort": "high"
+  },
+  "hardware": "NVIDIA RTX PRO 6000 Blackwell 96GB (Linux); Apple M5 24GB for Mac checks",
+  "date": "2026-09-23",
+  "source_repository": "apus-ailab/APUS-OpenJev-v1-35B-A3B",
+  "source_revision": "4947385291375f6f5149b3156ff2811c65ebf020",
+  "base_model": "Qwen/Qwen3.5-35B-A3B"
+}

conversion.json

@@ -0,0 +1,333 @@
+{
+  "source_snapshot": "/workspace/ms-swift-jev/gguf-release-20260923/src/35B-A3B",
+  "recipe": {
+    "mode": "affine",
+    "bits": 8,
+    "group_size": 64
+  },
+  "quantization": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine",
+    "language_model.model.layers.0.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.6.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.9.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.12.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.18.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.21.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.24.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.30.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.33.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.36.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    }
+  }
+}

evaluation/mlx-8bit.summary.json

@@ -0,0 +1,35 @@
+{
+  "variant": "35B-A3B-MLX-8bit",
+  "backend": "mlx 0.32.2 on Linux x86_64 (Device(gpu, 0))",
+  "rows": 80,
+  "correct": 71,
+  "reference_correct": 71,
+  "decision_agreement": 80,
+  "changed_panel_indexes": [],
+  "max_abs_probability_delta": 0.1930832862854004,
+  "mean_abs_probability_delta": 0.00731312684911245,
+  "peak_memory_gb": 38.66,
+  "seconds": 279.82,
+  "by_family": {
+    "browser": {
+      "rows": 16,
+      "correct": 13
+    },
+    "hs3": {
+      "rows": 16,
+      "correct": 14
+    },
+    "boolq": {
+      "rows": 16,
+      "correct": 16
+    },
+    "mnli": {
+      "rows": 16,
+      "correct": 13
+    },
+    "score": {
+      "rows": 16,
+      "correct": 15
+    }
+  }
+}

examples/openjev_mlx.py

@@ -0,0 +1,90 @@
+"""Run APUS-OpenJev MLX on Apple Silicon: exact candidate distribution with mlx-lm.
+
+    pip install mlx-lm
+    python examples/openjev_mlx.py --model apus-ailab/APUS-OpenJev-v1-4B-MLX-8bit
+
+The prompt is rendered by ``openjev_contracts.py`` (identical to the training
+contract) inside the no-thinking chat turn; the candidate labels A..P are single
+tokens and the distribution is the softmax of their final-position logits.
+"""
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+import mlx.core as mx
+from mlx_lm import load
+from mlx_lm.models.cache import make_prompt_cache
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+from openjev_contracts import format_response, label_mapping, render_prompt  # noqa: E402
+
+MAX_TOKENS = 8192
+PREFILL_STEP = 512  # chunked prefill keeps long prompts within unified memory
+
+
+class OpenJevMLX:
+    def __init__(self, model_path):
+        self.model, self.tokenizer = load(model_path)
+
+    def compile(self, request):
+        mapping = label_mapping(request)
+        prompt = self.tokenizer.apply_chat_template(
+            [{"role": "user", "content": render_prompt(request)}],
+            tokenize=False,
+            add_generation_prompt=True,
+            enable_thinking=False,
+        )
+        ids = self.tokenizer.encode(prompt, add_special_tokens=False)
+        if not ids or len(ids) > MAX_TOKENS:
+            raise ValueError("input exceeds 8192 tokens; no truncation is performed")
+        candidates = []
+        for label in mapping:
+            token = self.tokenizer.encode(label, add_special_tokens=False)
+            if (
+                len(token) != 1
+                or self.tokenizer.encode(prompt + label, add_special_tokens=False)
+                != ids + token
+            ):
+                raise ValueError(
+                    "candidate label is not a single token at the answer boundary"
+                )
+            candidates.append(token[0])
+        return ids, candidates
+
+    def decide(self, request):
+        ids, candidates = self.compile(request)
+        cache = make_prompt_cache(self.model)
+        for start in range(0, len(ids) - 1, PREFILL_STEP):
+            self.model(
+                mx.array([ids[start : min(start + PREFILL_STEP, len(ids) - 1)]]),
+                cache=cache,
+            )
+            mx.eval([c.state for c in cache])
+        logits = self.model(mx.array([ids[-1:]]), cache=cache)[0, -1].astype(
+            mx.float32
+        )[mx.array(candidates)]
+        response = format_response(request, mx.softmax(logits).tolist())
+        response.update(prompt_tokens=len(ids), calibrated=False)
+        return response
+
+
+EXAMPLE = {
+    "id": "support-731",
+    "group_id": "support-731",
+    "primitive": "choice",
+    "state": "Order 731 was delivered. The customer confirms that the issue is resolved.",
+    "instructions": "Select the next support action.",
+    "criteria": [
+        {"id": "close_ticket", "description": "Close the ticket as resolved."},
+        {"id": "escalate", "description": "Escalate to a human agent."},
+        {"id": "refund", "description": "Issue a refund."},
+    ],
+}
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model", required=True, help="local directory or HF repo id")
+    args = parser.parse_args()
+    print(json.dumps(OpenJevMLX(args.model).decide(EXAMPLE), indent=2))

generation_config.json

@@ -0,0 +1,13 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "4.57.0.dev0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb31d46ea29bb4429b828548f9be2080ccd8ba8f278db777bef6c33aa3df5db6
+size 5332147837

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3299609e945c61d3ac5efdac529c07e885e2d3e23d1f8130de06d1930c86c7f1
+size 5358685713

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38d143b3f4dd22a12bc7e7d98a2277fa78b3eec1d2b1cb5e6d48de84a4fb8827
+size 5365575812

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c3f4d1adfde9574e8816ed5fd543a8befa928c2350d0fc2aa38d9d45c3d19c
+size 5358685928

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1157d29c8c9adbe7d90652600a117ddc8e25cff3313564288cf70abe9b21628e
+size 5365575810

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421376fe42ed238918fa499373a760e8894e58d8bb6b28e6be07db58bc4f98ed
+size 5358685910

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5477a20a735dea1b19b2c5f4500586633cad8f41b36c4fab579aa4f2687318
+size 4688875091

openjev_contracts.py

@@ -0,0 +1,102 @@
+"""Small shared contract. Prompts use a strict whitelist of input fields."""
+
+import json
+import math
+
+PROMPT_VERSION = "jev.dynamic.prompt.v2"
+LABELS = tuple("ABCDEFGHIJKLMNOP")
+BINARY_CRITERIA = [
+    {"id": "yes", "description": "The stated proposition is true."},
+    {"id": "no", "description": "The stated proposition is false."},
+]
+
+
+def validate_request(record):
+    for key in ("id", "group_id", "state", "instructions"):
+        if not isinstance(record.get(key), str) or not record[key].strip():
+            raise ValueError(f"{key} must be a nonempty string")
+    if record.get("primitive") not in ("choice", "noul", "score_level"):
+        raise ValueError("unsupported primitive")
+    criteria = record.get("criteria")
+    if not isinstance(criteria, list) or not 2 <= len(criteria) <= len(LABELS):
+        raise ValueError("criteria must contain 2..16 candidates")
+    ids = []
+    for candidate in criteria:
+        if not isinstance(candidate, dict):
+            raise TypeError("candidate must be an object")
+        for key in ("id", "description"):
+            if not isinstance(candidate.get(key), str) or not candidate[key].strip():
+                raise ValueError(f"candidate {key} must be nonempty")
+        ids.append(candidate["id"])
+    if len(set(ids)) != len(ids):
+        raise ValueError("duplicate candidate ids")
+    if record["primitive"] != "choice" and criteria != BINARY_CRITERIA:
+        raise ValueError("noul and score_level require canonical yes/no criteria")
+
+
+def validate_record(record):
+    validate_request(record)
+    if record.get("gold") not in [c["id"] for c in record["criteria"]]:
+        raise ValueError("gold must be a candidate id")
+    if not isinstance(record.get("provenance"), dict):
+        raise TypeError("provenance must be an object")
+
+
+def label_mapping(record):
+    validate_request(record)
+    return dict(zip(LABELS, (c["id"] for c in record["criteria"])))
+
+
+def render_prompt_parts(record):
+    """Text prefix/suffix; callers MUST check tokenizer boundary equivalence."""
+    validate_request(record)
+    prefix = "Shared state:\n" + record["state"] + "\n\n"
+    task = {
+        "primitive": record["primitive"],
+        "instructions": record["instructions"],
+        "criteria": [
+            {"label": label, "description": candidate["description"]}
+            for label, candidate in zip(LABELS, record["criteria"])
+        ],
+    }
+    suffix = json.dumps(task, ensure_ascii=False, sort_keys=True)
+    suffix += (
+        "\nReturn only the selected letter: "
+        + ", ".join(LABELS[: len(record["criteria"])])
+        + ".\nAnswer:"
+    )
+    return prefix, suffix
+
+
+def render_prompt(record):
+    return "".join(render_prompt_parts(record))
+
+
+def to_messages(record):
+    validate_record(record)
+    inverse = {candidate: label for label, candidate in label_mapping(record).items()}
+    return {
+        "messages": [
+            {"role": "user", "content": render_prompt(record)},
+            {"role": "assistant", "content": inverse[record["gold"]]},
+        ]
+    }
+
+
+def format_response(record, probabilities):
+    """Map ordered candidate probabilities; score_level is NOT aggregate Score."""
+    mapping = label_mapping(record)
+    values = list(probabilities)
+    if len(values) != len(mapping) or any(
+        not math.isfinite(p) or p < 0 or p > 1 for p in values
+    ):
+        raise ValueError("invalid probabilities")
+    if not math.isclose(sum(values), 1, abs_tol=1e-5):
+        raise ValueError("probabilities must sum to one")
+    distribution = dict(zip(mapping.values(), values))
+    result = {"type": record["primitive"], "probabilities": distribution}
+    if record["primitive"] == "choice":
+        result["choice"] = max(distribution, key=distribution.get)
+    else:
+        result["yes_probability"] = distribution["yes"]
+    return result

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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "tool_parser_type": "qwen3_coder",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}