初始化项目，由ModelHub XC社区提供模型

Model: qvac/MedPsy-4B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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

.gitignore

@@ -0,0 +1 @@
+/assets/

LICENSE

@@ -0,0 +1,178 @@
+
+                                 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
+

README.md

@@ -0,0 +1,252 @@
+---
+language:
+- en
+license: apache-2.0
+license_link: https://huggingface.co/qvac/MedPsy-4B/blob/main/LICENSE
+library_name: transformers
+base_model:
+- Qwen/Qwen3-4B-Thinking-2507
+tags:
+- medical
+- healthcare
+- clinical
+- edge
+- qwen3
+- tether-ai
+- text-generation
+- on-device
+pipeline_tag: text-generation
+---
+
+# MedPsy-4B
+
+**MedPsy-4B** is a state-of-the-art, text-only medical and healthcare language model purpose-built for edge deployment. Built on top of Qwen3-4B-Thinking-2507 and post-trained with a multi-stage pipeline (supervised fine-tuning + reinforcement learning) on curated medical data, it surpasses models nearly 7x its size on medical benchmarks.
+
+| | |
+|:---|:---|
+| **Developed by** | [Tether AI Research](https://tether.io/) |
+| **Model type** | Text-only causal language model (decoder-only transformer) |
+| **Base model** | [Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) |
+| **Language** | English |
+| **License** | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) |
+| **Technical report** | [MedPsy Technical Report](https://huggingface.co/blog/qvac/medpsy) |
+| **Collection** | [MedPsy on Hugging Face](https://huggingface.co/collections/qvac/medpsy) |
+| **All MedPsy variants** | [MedPsy-4B](https://huggingface.co/qvac/MedPsy-4B) · [MedPsy-1.7B](https://huggingface.co/qvac/MedPsy-1.7B) · [MedPsy-4B-GGUF](https://huggingface.co/qvac/MedPsy-4B-GGUF) · [MedPsy-1.7B-GGUF](https://huggingface.co/qvac/MedPsy-1.7B-GGUF) |
+
+## Key Highlights
+
+- **Surpasses 27B models at 4B scale**: Scores **70.54** on closed-ended medical benchmarks, outperforming MedGemma-27B-text-it (69.95) despite being nearly 7x smaller
+- **Real-world clinical strength**: Achieves **74.00** on HealthBench and **58.00** on HealthBench Hard, beating MedGemma-27B (65.00 / 42.00) by +9.00 and +16.00 points
+- **3.2x token efficiency**: Produces accurate medical answers in ~909 tokens vs ~2,953 for Qwen3-4B Thinking, reducing latency and compute cost
+- **Privacy-first**: Enables fully on-device inference via the [QVAC SDK](https://qvac.tether.io/dev/sdk/) and [QVAC 
+Fabric](https://huggingface.co/blog/qvac/fabric-llm-finetune), patient data never leaves the device.
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66ad47f5a45133da70d1c40b/F-8t5tIM8oSqVrOXWNl2F.png" alt="MedPsy 4B: Benchmarks" width="1000">
+</p>
+## Benchmark Results
+
+
+
+<table style="width:100%; border-collapse:collapse; font-size:14px;">
+  <thead>
+    <tr>
+      <th style="padding:10px 14px; text-align:left; border-bottom:2px solid #ddd;"></th>
+      <th style="padding:10px 14px; text-align:center; border-bottom:2px solid #ddd; color:#009393; font-weight:bold;">MedPsy-4B</th>
+      <th style="padding:10px 14px; text-align:center; border-bottom:2px solid #ddd; color:#009393; font-weight:bold;">MedGemma-27B-text-it</th>
+      <th style="padding:10px 14px; text-align:center; border-bottom:2px solid #ddd; color:#009393; font-weight:bold;">Qwen3-4B-Thinking-2507</th>
+      <th style="padding:10px 14px; text-align:center; border-bottom:2px solid #ddd; color:#009393; font-weight:bold;">MedGemma-1.5-4B-it</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="background:rgba(0,147,147,0.08);"><td colspan="5" style="padding:10px 14px; font-weight:bold; color:#009393; border-bottom:2px solid #009393;">Closed-Ended Medical Benchmarks</td></tr>
+    <tr><td style="padding:8px 14px;">Average</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">70.54</td><td style="padding:8px 14px; text-align:center;">69.95</td><td style="padding:8px 14px; text-align:center;">63.10</td><td style="padding:8px 14px; text-align:center;">51.20</td></tr>
+    <tr><td style="padding:8px 14px;">MMLU (Health)</td><td style="padding:8px 14px; text-align:center;">89.70</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">90.48</td><td style="padding:8px 14px; text-align:center;">85.92</td><td style="padding:8px 14px; text-align:center;">67.69</td></tr>
+    <tr><td style="padding:8px 14px;">AfriMedQA</td><td style="padding:8px 14px; text-align:center;">71.50</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">73.07</td><td style="padding:8px 14px; text-align:center;">64.12</td><td style="padding:8px 14px; text-align:center;">54.38</td></tr>
+    <tr><td style="padding:8px 14px;">MMLU-Pro Health</td><td style="padding:8px 14px; text-align:center;">70.45</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">72.94</td><td style="padding:8px 14px; text-align:center;">67.73</td><td style="padding:8px 14px; text-align:center;">47.31</td></tr>
+    <tr><td style="padding:8px 14px;">MedMCQA</td><td style="padding:8px 14px; text-align:center;">72.15</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">72.77</td><td style="padding:8px 14px; text-align:center;">61.78</td><td style="padding:8px 14px; text-align:center;">50.08</td></tr>
+    <tr><td style="padding:8px 14px;">MedQA (USMLE)</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">84.39</td><td style="padding:8px 14px; text-align:center;">83.29</td><td style="padding:8px 14px; text-align:center;">70.91</td><td style="padding:8px 14px; text-align:center;">64.39</td></tr>
+    <tr><td style="padding:8px 14px;">MedXpertQA</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">30.61</td><td style="padding:8px 14px; text-align:center;">25.18</td><td style="padding:8px 14px; text-align:center;">16.69</td><td style="padding:8px 14px; text-align:center;">15.80</td></tr>
+    <tr><td style="padding:8px 14px;">PubMedQA</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">75.00</td><td style="padding:8px 14px; text-align:center;">71.93</td><td style="padding:8px 14px; text-align:center;">74.53</td><td style="padding:8px 14px; text-align:center;">58.73</td></tr>
+    <tr style="background:rgba(0,147,147,0.08);"><td colspan="5" style="padding:10px 14px; font-weight:bold; color:#009393; border-bottom:2px solid #009393;">HealthBench</td></tr>
+    <tr><td style="padding:8px 14px;">Overall</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">74.00</td><td style="padding:8px 14px; text-align:center;">65.00</td><td style="padding:8px 14px; text-align:center;">63.00</td><td style="padding:8px 14px; text-align:center;">54.00</td></tr>
+    <tr><td style="padding:8px 14px;">Expertise-Tailored Communication</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">79.33</td><td style="padding:8px 14px; text-align:center;">73.00</td><td style="padding:8px 14px; text-align:center;">71.00</td><td style="padding:8px 14px; text-align:center;">62.67</td></tr>
+    <tr><td style="padding:8px 14px;">Response Depth</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">63.67</td><td style="padding:8px 14px; text-align:center;">61.33</td><td style="padding:8px 14px; text-align:center;">58.00</td><td style="padding:8px 14px; text-align:center;">48.67</td></tr>
+    <tr><td style="padding:8px 14px;">Context Seeking</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">71.67</td><td style="padding:8px 14px; text-align:center;">58.67</td><td style="padding:8px 14px; text-align:center;">57.67</td><td style="padding:8px 14px; text-align:center;">46.00</td></tr>
+    <tr><td style="padding:8px 14px;">Emergency Referrals</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">81.67</td><td style="padding:8px 14px; text-align:center;">73.00</td><td style="padding:8px 14px; text-align:center;">74.00</td><td style="padding:8px 14px; text-align:center;">64.00</td></tr>
+    <tr><td style="padding:8px 14px;">Global Health</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">73.67</td><td style="padding:8px 14px; text-align:center;">61.00</td><td style="padding:8px 14px; text-align:center;">59.00</td><td style="padding:8px 14px; text-align:center;">47.67</td></tr>
+    <tr><td style="padding:8px 14px;">Health Data Tasks</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">60.67</td><td style="padding:8px 14px; text-align:center;">56.67</td><td style="padding:8px 14px; text-align:center;">54.67</td><td style="padding:8px 14px; text-align:center;">44.67</td></tr>
+    <tr><td style="padding:8px 14px;">Responding Under Uncertainty</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">76.33</td><td style="padding:8px 14px; text-align:center;">66.33</td><td style="padding:8px 14px; text-align:center;">64.33</td><td style="padding:8px 14px; text-align:center;">58.33</td></tr>
+    <tr style="background:rgba(0,147,147,0.08);"><td colspan="5" style="padding:10px 14px; font-weight:bold; color:#009393; border-bottom:2px solid #009393;">HealthBench Hard</td></tr>
+    <tr><td style="padding:8px 14px;">Overall</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">58.00</td><td style="padding:8px 14px; text-align:center;">42.00</td><td style="padding:8px 14px; text-align:center;">42.67</td><td style="padding:8px 14px; text-align:center;">29.67</td></tr>
+    <tr><td style="padding:8px 14px;">Expertise-Tailored Communication</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">55.33</td><td style="padding:8px 14px; text-align:center;">44.67</td><td style="padding:8px 14px; text-align:center;">45.00</td><td style="padding:8px 14px; text-align:center;">31.67</td></tr>
+    <tr><td style="padding:8px 14px;">Response Depth</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">47.67</td><td style="padding:8px 14px; text-align:center;">38.67</td><td style="padding:8px 14px; text-align:center;">38.67</td><td style="padding:8px 14px; text-align:center;">29.00</td></tr>
+    <tr><td style="padding:8px 14px;">Context Seeking</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">63.33</td><td style="padding:8px 14px; text-align:center;">42.00</td><td style="padding:8px 14px; text-align:center;">43.00</td><td style="padding:8px 14px; text-align:center;">28.00</td></tr>
+    <tr><td style="padding:8px 14px;">Emergency Referrals</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">62.33</td><td style="padding:8px 14px; text-align:center;">39.67</td><td style="padding:8px 14px; text-align:center;">47.33</td><td style="padding:8px 14px; text-align:center;">29.00</td></tr>
+    <tr><td style="padding:8px 14px;">Global Health</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">60.00</td><td style="padding:8px 14px; text-align:center;">42.67</td><td style="padding:8px 14px; text-align:center;">43.33</td><td style="padding:8px 14px; text-align:center;">29.00</td></tr>
+    <tr><td style="padding:8px 14px;">Health Data Tasks</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">46.67</td><td style="padding:8px 14px; text-align:center;">39.33</td><td style="padding:8px 14px; text-align:center;">39.67</td><td style="padding:8px 14px; text-align:center;">23.67</td></tr>
+    <tr><td style="padding:8px 14px;">Responding Under Uncertainty</td><td style="padding:8px 14px; text-align:center; font-weight:bold;">61.00</td><td style="padding:8px 14px; text-align:center;">42.67</td><td style="padding:8px 14px; text-align:center;">42.00</td><td style="padding:8px 14px; text-align:center;">35.00</td></tr>
+  </tbody>
+</table>
+
+<p style="font-size:11px; color:#888; margin-top:8px; line-height:1.6;">
+* MMLU (Health): averaged accuracy across 6 sub-domains: anatomy, clinical_knowledge, college_biology, college_medicine, medical_genetics, professional_medicine.<br>
+* HealthBench evaluated using CompassJudger-2-32B-Instruct as judge.<br>
+* All results are averaged over 3 runs with generation parameters: temperature=0.6, top_k=20, top_p=0.95, max_output_tokens=16384.
+</p>
+
+## Token Efficiency
+
+Beyond raw accuracy, MedPsy-4B achieves a **3.2x reduction** in average response length compared to its backbone model (Qwen3-4B-Thinking-2507). This means faster inference, lower compute costs, and reduced latency - critical for real-time clinical decision support on edge devices.
+
+<table style="width:80%; border-collapse:collapse; font-size:14px; margin:auto;">
+  <thead>
+    <tr>
+      <th style="padding:10px 18px; text-align:left; border-bottom:2px solid #ddd;"></th>
+      <th style="padding:10px 18px; text-align:center; border-bottom:2px solid #ddd;">Qwen3-4B-Thinking-2507</th>
+      <th style="padding:10px 18px; text-align:center; border-bottom:2px solid #ddd; color:#009393; font-weight:bold;">MedPsy-4B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="padding:8px 14px; font-weight:bold;">Avg. Response Length (Tokens)</td>
+      <td style="padding:8px 14px; text-align:center;">2,953</td>
+      <td style="padding:8px 14px; text-align:center; font-weight:bold;">909</td>
+    </tr>
+    <tr style="background:rgba(0,147,147,0.08); border-top:2px solid #009393;">
+      <td style="padding:8px 14px; font-weight:bold; color:#009393;">Δ Reduction</td>
+      <td colspan="2" style="padding:8px 14px; text-align:center; font-weight:bold; color:#009393; font-size:16px;">3.2x fewer tokens</td>
+    </tr>
+  </tbody>
+</table>
+
+The chart below shows per-benchmark response lengths. The largest reductions appear on reasoning-intensive tasks (MedXpertQA, MedQA-USMLE, MMLU-Pro Health), where the base model's extended thinking produces substantially longer outputs without accuracy gains over our post-trained model.
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66ad47f5a45133da70d1c40b/MFVmKNNxen-axlV06TnTY.png" alt="Average Response Length (Tokens) - 4B model class" width="700">
+</p>
+
+<p align="center"><em>Average response length (tokens) per benchmark. Lower is better. MedPsy-4B consistently produces shorter responses than Qwen3-4B-Thinking-2507 while achieving higher overall accuracy.</em></p>
+
+## Model Details
+
+| Parameter | Value |
+|:---|:---|
+| Architecture | Qwen3ForCausalLM |
+| Parameters | 4B |
+| Hidden size | 2,560 |
+| FFN hidden size | 9,728 |
+| Layers | 36 |
+| Attention heads | 32 |
+| KV groups (GQA) | 8 |
+| Vocab size | 151,936 |
+| Max position embeddings | 262,144 |
+| Precision | bfloat16 |
+| Position embedding | RoPE |
+| Normalization | RMSNorm |
+| Activation | SwiGLU |
+
+## Usage
+
+### Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "qvac/MedPsy-4B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+
+messages = [
+    {"role": "user", "content": "What are the common symptoms and first-line treatments for community-acquired pneumonia?"}
+]
+
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=1024)
+response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
+print(response)
+```
+
+## Training
+
+The model was post-trained through a multi-stage pipeline on the Qwen3-4B-Thinking-2507 backbone:
+
+1. **SFT Stage 1 (Corpus 1)**: Broad medical adaptation on a large-scale synthetic corpus spanning biology, medicine, and health (including a new health domain not yet publicly released), built from [Genesis II](https://huggingface.co/blog/qvac/genesis-ii)–style medical seeds and open-source medical QA prompts used purely as questions, with all reasoning targets freshly generated by [Baichuan-M3-235B](https://huggingface.co/baichuan-inc/Baichuan-M3-235B).
+2. **SFT Stage 2 (Corpus 2)**: Reasoning specialization on a smaller, higher-value clinical QA corpus with teacher-generated chain-of-thought reasoning from Baichuan-M3-235B.
+3. **RL Stage 1**: Reinforcement learning (DAPO) on the easy/moderate subset of AlphaMedQA ([Liu et al., 2025](https://arxiv.org/abs/2505.17952)), annotated with the SFT checkpoint.
+4. **RL Stage 2**: Focused RL on a hard-enriched AlphaMedQA subset re-annotated with the best Stage 1 checkpoint, targeting persistent failure modes.
+
+For full methodology details, see the [MedPsy Technical Report](https://huggingface.co/blog/qvac/medpsy).
+
+
+## Use and Limitations
+
+### Intended Use
+
+MedPsy-4B is an open language model intended as a **starting point for developers and researchers** building downstream healthcare applications involving medical text. Developers are expected to validate, adapt, and make meaningful modifications to the model for their specific use cases.
+
+Appropriate use cases include:
+- Research on medical language understanding and reasoning
+- Building developer tools and prototypes for health-related applications
+- On-device medical information retrieval for privacy-sensitive environments
+
+Always with appropriate disclaimers.
+
+### Limitations
+
+> [!WARNING]
+> This model is **NOT a substitute for professional medical judgment** and the model outputs are **NOT a substitute for proper clinical diagnosis**. Always consult with a certified physician. Despite strong benchmark performance, MedPsy-4B is a compact 4B-parameter language model that **will make errors**. Medical AI systems can produce outputs that appear confident and authoritative while being factually incorrect, incomplete, or clinically inappropriate.
+
+**Known limitations include:**
+
+- **Hallucinations**: The model may generate plausible-sounding but incorrect medical information.
+- **English only**: The model was trained and evaluated primarily in English. Performance in other languages is not validated.
+- **Text only**: This model processes text inputs only. It cannot interpret medical images, lab results in non-text formats, or other modalities.
+- **No real-time knowledge**: The model's knowledge has a training data cutoff and does not reflect the latest medical guidelines, drug approvals, or clinical evidence.
+- **Bias in training data**: As with any model trained on synthetic and public medical data, biases in the source material may propagate to model outputs. Developers should validate performance across diverse patient populations, demographics, and clinical contexts.
+- **Not designed for emergencies**: This model should never be used as the sole decision-making tool in emergency or life-threatening situations.
+
+### Safety Recommendations
+
+When integrating this model into any application:
+
+1. **Always include visible disclaimers** informing users that outputs are AI-generated and not a substitute for professional medical advice
+2. **Do not use for direct clinical diagnosis or treatment** without oversight by qualified healthcare professionals
+3. **Monitor for harmful outputs** and implement appropriate safety filters in production systems
+
+## Ethics and Safety
+
+The model was evaluated on medical safety dimensions through the HealthBench evaluation framework, which assesses Emergency Referrals, Responding Under Uncertainty, and Context Seeking, all critical safety dimensions for medical AI. However, no dedicated red-teaming or adversarial safety testing has been conducted on this model to date. Developers deploying this model in production should conduct their own safety evaluations appropriate to their use case.
+
+## Related Resources
+
+- [MedPsy Collection](https://huggingface.co/collections/qvac/medpsy): All MedPsy models, datasets, and resources in one place
+- [MedPsy Technical Report](https://huggingface.co/blog/qvac/medpsy): Full methodology and ablation details
+- [MedPsy-1.7B](https://huggingface.co/qvac/MedPsy-1.7B): Smaller sibling model for smartphone-class deployment
+- [MedPsy-4B-GGUF](https://huggingface.co/qvac/MedPsy-4B-GGUF): Quantized GGUF weights for on-device inference via llama.cpp / QVAC SDK
+- [QVAC SDK](https://qvac.tether.io/dev/sdk/): On-device AI deployment framework
+- [QVAC Genesis II](https://huggingface.co/blog/qvac/genesis-ii): Underlying data generation methodology
+
+## Citation
+
+```bibtex
+@article{medpsy2026,
+  title={MedPsy: State-of-the-Art Medical and Healthcare Language Models for Edge Devices},
+  author={Vitabile, Davide and Buffa, Alexandro and Nambiar, Akshay and Nazir, Amril},
+  year={2026},
+  url={https://huggingface.co/blog/qvac/medpsy}
+  institution={Tether AI Research}
+}
+```
+
+## Copyright
+
+We will take appropriate actions in response to notices of copyright infringement. If you believe your work has been used or copied in a manner that infringes upon your intellectual property rights, please email [data-apps@tether.io](mailto:data-apps@tether.io) identifying and describing both the copyrighted work and alleged infringing content.
+
+## Licensing
+
+This model, which was trained as described in the [MedPsy Technical Report](https://huggingface.co/blog/qvac/medpsy), is licensed by Tether Data, S.A. de C.V. under the [Apache 2.0 license](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) for research and educational purposes. As described above, this model is a version of [Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507), which is also under the [Apache 2.0 license](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
+
+As described above, a subset of the Genesis I and Genesis II datasets was used by the [Baichuan-M3-235B](https://huggingface.co/baichuan-inc/Baichuan-M3-235B) model—which itself is also available under the [Apache 2.0 license](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) to generate synthetic data for training this model. The [Genesis I](https://huggingface.co/datasets/qvac/GenesisI) dataset is made available under the [CC-BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.en) (Creative Commons Attribution-NonCommercial 4.0) license. The [Genesis II](https://huggingface.co/datasets/qvac/GenesisII) dataset is also made available under the [CC-BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.en) license.

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d46d55174f7c049eb40575c8b4b2b43bba9893cf3dc66fad2f899a64b2d115a
+size 8822894520

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "151643": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151644": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151645": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151646": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151647": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151648": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151649": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151650": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151651": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151652": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151653": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151654": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151655": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151656": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "151657": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151658": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151659": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151660": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151661": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151662": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151663": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151664": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151665": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151666": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151667": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "151668": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        }
+    },
+    "additional_special_tokens": [
+        "<|im_start|>",
+        "<|im_end|>",
+        "<|object_ref_start|>",
+        "<|object_ref_end|>",
+        "<|box_start|>",
+        "<|box_end|>",
+        "<|quad_start|>",
+        "<|quad_end|>",
+        "<|vision_start|>",
+        "<|vision_end|>",
+        "<|vision_pad|>",
+        "<|image_pad|>",
+        "<|video_pad|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set persona = 'You are MedPsy, a medical and healthcare AI assistant developed by QVAC.' %}\n\n{%- if tools %}\n    {{- '<|im_start|>system\\n' + persona }}\n    {%- if messages[0].role == 'system' %}\n        {{- '\\n' + messages[0].content }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {{- '<|im_start|>system\\n' + persona }}\n    {%- if messages[0].role == 'system' %}\n        {{- '\\n' + messages[0].content }}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n\n        {{- '<|im_start|>' + message.role }}\n        {% generation %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- content }}\n            {%- endif %}\n        {%- else %}\n            {{- content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>' }}\n        {% endgeneration %}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false
+}