lastmass/Qwen3.5-Medical-GSPO
https://huggingface.co/lastmass/Qwen3.5-Medical-GSPOA Chinese medical reasoning model fine-tuned from Qwen3.5-4B using a two-stage training pipeline: Supervised Fine-Tuning (SFT) for format alignment, followed by Group Sequence Policy Optimization (GSPO) with an LLM-as-Judge reward function.
Sourced from
- HuggingFace — lastmass/Qwen3.5-Medical-GSPO
Related resources
!Screenshot 2026-07-05 at 2.33.47 AM
Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding
🩺 HealthGPT-Pro: A High-Performance Multimodal Large Language Model for Medical Understanding and Analysis
First architecture deeply integrating a DNA foundation model with an LLM for multimodal biological reasoning, achieving 98% accuracy on KEGG disease pathway prediction and 15%+ average gains on variant effect prediction with interpretable step-by-step reasoning traces (bowang-lab, 390+ stars)