hugpadhugpad

FreedomIntelligence / HuatuoGPT-3-27B

Vision3M1.4K9Updated Sep 24, 2026
Hugging Face

Downloads

1.4K

Likes

9

Last updated

Sep 24, 2026

License

apache-2.0

HuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning. Teacher responses provide temporary gu…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5
  • image-text-to-text
  • medical
  • reasoning
  • conversational

Technical specifications

Parameters3M
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0