Update Hulu-Med-4B

README.md

@@ -27,12 +27,15 @@ library_name: transformers
 [![ModelScope](https://img.shields.io/badge/ModelScope-Models-blue)](https://modelscope.cn/models/Med-Team/Hulu-Med)
 [![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](LICENSE)
 [![GitHub](https://img.shields.io/badge/GitHub-Code-blue?logo=github)](https://github.com/ZJUI-AI4H/Hulu-Med)
+![Total Downloads](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2FZJU-AI4H%2FHulu-Med-14B%3Fexpand%255B%255D%3DdownloadsAllTime&query=%24.downloadsAllTime&label=Total%20Downloads&color=blue)
 
-[📄 Paper](http://arxiv.org/abs/2510.08668) | [🤗 Hulu-Med-7B](https://huggingface.co/ZJU-AI4H/Hulu-Med-7B) |[🤗 Hulu-Med-14B](https://huggingface.co/ZJU-AI4H/Hulu-Med-14B) |[🤗 Hulu-Med-32B](https://huggingface.co/ZJU-AI4H/Hulu-Med-32B) | [🔮 ModelScope Models](https://modelscope.cn/models/Med-Team/Hulu-Med) | [📊 Demo](#demo)
+[📄 Paper](http://arxiv.org/abs/2510.08668) | [🤗 Hulu-Med-4B](https://huggingface.co/ZJU-AI4H/Hulu-Med-4B) | [🤗 Hulu-Med-7B](https://huggingface.co/ZJU-AI4H/Hulu-Med-7B) |[🤗 Hulu-Med-14B](https://huggingface.co/ZJU-AI4H/Hulu-Med-14B) |[🤗 Hulu-Med-32B](https://huggingface.co/ZJU-AI4H/Hulu-Med-32B) | [🔮 ModelScope Models](https://modelscope.cn/models/Med-Team/Hulu-Med) | [📊 Demo](#demo)
 
 </div>
 
 ## 🔥 News
+- **[2025-11-18]** 🎊 We released **Hulu-Med-4B**, a lightweight model with strong multimodal and text reasoning abilities that surpasses **MedGemma-4B** and **Lingshu-7B**!
+
 - **[2025-11-01]** 📊 Releasing our new evaluation code, **MedUniEval**! Built on MedEvalKit, MedUniEval is designed for the comprehensive evaluation of medical visual-language models across various modalities—including text, 2D, 3D, and video. More benchmarks are coming soon.
   
 - **[2025-10-15]** 🎉 Hulu-Med now supports Transformers integration! HuggingFace-compatible models released with simplified loading and inference. Integration with VLLM is ongoing. *The HF models are now available in the **main branch** on Hugging Face*.
@@ -67,6 +70,8 @@ Our training corpus encompasses:
 
 ## 🏆 Performance Highlights
 
+## 🏆 Performance Highlights
+
 ### Medical Multimodal Benchmarks
 
 Performance comparison on medical multimodal benchmarks (For the 'Medical VLM < 10B' subgroup, **bold** indicates the best method):
@@ -91,6 +96,7 @@ Performance comparison on medical multimodal benchmarks (For the 'Medical VLM <
 | MedGemma-4B | 70.7 | 49.2 | 72.3 | 78.2 | 48.1 | 25.4 | 43.2 |
 | HuatuoGPT-V-7B | 74.3 | 53.1 | 67.6 | 68.1 | 44.8 | 23.2 | 49.8 |
 | Lingshu-7B | 82.9 | 56.3 | 67.9 | 83.1 | 61.9 | 26.7 | - |
+| **Hulu-Med-4B** | **81.6** | **64.6** | **71.6** | **85.0** | **60.1** | **26.4** | **50.5** |
 | **Hulu-Med-7B** | **84.2** | **66.8** | **78.0** | **86.8** | **65.6** | **29.0** | **51.4** |
 | **Medical VLMs > 10B** |
 | HealthGPT-14B | 75.2 | 56.4 | 65.0 | 66.1 | 56.7 | 24.7 | 49.6 |
@@ -123,6 +129,7 @@ Performance comparison on medical text benchmarks (**bold** indicates the best m
 | MedGemma-4B | 38.6 | 12.8 | 45.6 | 21.6 | 72.2 | 52.2 | 56.2 | 66.7 |
 | HuatuoGPT-V-7B | 44.6 | 10.1 | 40.9 | 21.9 | 72.8 | 51.2 | 52.9 | 69.3 |
 | Lingshu-7B | 50.4 | 16.5 | 56.2 | 26.3 | 76.6 | 55.9 | 63.3 | 74.5 |
+| **Hulu-Med-4B** | **58.6** | **16.8** | **59.4** | **29.5** | **77.6** | **64.8** | **71.9** | **78.6** |
 | **Hulu-Med-7B** | **60.6** | **19.6** | **61.5** | **31.1** | **77.4** | **67.6** | **73.5** | **79.5** |
 | **Medical VLMs > 10B** |
 | HealthGPT-14B | 63.4 | 11.3 | 39.8 | 25.7 | 68.0 | 63.4 | 66.2 | 80.2 |