lastmass/Qwen3.5-Medical-GSPO

https://huggingface.co/lastmass/Qwen3.5-Medical-GSPO
Activeby lastmass6.2K12updated 1 month ago

A 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

  • HuggingFacelastmass/Qwen3.5-Medical-GSPO

Related resources

!image

Active5833 months ago
Python

!Screenshot 2026-07-05 at 2.33.47 AM

Active1.1K3 weeks ago
Python

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Active7241 month ago
Python

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)

Active3981 month ago
Jupyter Notebook
Apache-2.0

In search enginers, rerankers are crucial for improving the accuracy of your retrieval system.

Active22.9K4 months ago
Python
Stale5702 years ago
Python