lastmass/Qwen3.5-Medical-GSPO

Name: lastmass/Qwen3.5-Medical-GSPO
Author: lastmass

https://huggingface.co/lastmass/Qwen3.5-Medical-GSPO

Activeby lastmass6.2K12updated 4 months 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

HuggingFace — lastmass/Qwen3.5-Medical-GSPO

Related resources

FreedomIntelligence/HuatuoGPT-3-27B

by FreedomIntelligence

image-text-to-text

Model

🩺 HuatuoGPT-3-27B 🏠 GitHub | 📄 Paper

Active1201 month ago

Python

FreedomIntelligence/HuatuoGPT-3-9B

by FreedomIntelligence

image-text-to-text

Model

🩺 HuatuoGPT-3-9B 🏠 GitHub | 📄 Paper

Active5291 month ago

Python

lintw/HealthGPT-Pro-27B

by lintw

image-text-to-image

Model

🩺 HealthGPT-Pro: A High-Performance Multimodal Large Language Model for Medical Understanding and Analysis

Active2.1K2 months ago

OpenMed/Qwen3.5-2B-MedVL

by OpenMed

visual-question-answering

Model

!SynthVision

Active13.9K1 month ago

Simonlee711/MedJev

by Simonlee711

zero-shot-classification

Model

MedJev is [OpenJev Flash 9B] adapted to medicine. This repository adds a zero-shot medical evaluation, Open MedJev: How Far Do Zero-Shot System-One Decisions Go in Medicine?

Active362 days ago

Python

Jackrong/Qwopus3.5-27B-v3.5

by Jackrong

image-text-to-text

Model

!image

Idle6016 months ago

Python