# FreedomIntelligence/HuatuoGPT-o1

Medical o1, Towards medical complex reasoning with LLMs

Repository: https://github.com/FreedomIntelligence/HuatuoGPT-o1
Canonical: https://ross.abutalabs.com/products/huatuogpt-o1
Language: Python
License Family: other
Last push: 2025-01-20T02:31:13+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 2, release rhythm 35, longevity 44
- inputs: {"age_days": 619, "days_push": 591, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1349, forks 131 (observed 2026-08-28T04:04:27.886530+00:00)

## What it is
HuatuoGPT-o1 is a medical large language model project for complex medical reasoning, with open-sourced models (7B-72B), fine-tuning data, and training code. It uses a verifier-guided search and PPO reinforcement learning to improve reasoning quality.

## Use cases
- medical question answering with step-by-step reasoning
- fine-tune an LLM for complex medical reasoning
- train a medical LLM with reinforcement learning and verifier rewards
- deploy a medical chat model locally with vllm
- get a medical reasoning dataset for SFT
- build a healthcare AI assistant that checks its own reasoning

## When to choose
- you need an open medical LLM with strong chain-of-thought reasoning in English or Chinese
- you want to reproduce or extend verifier-based RL training for domain reasoning
- you need open weights and training data for medical AI research

## When to avoid
- you need a clinically validated, certified medical device for patient care
- you need multilingual support beyond English and Chinese
- you want a hosted API without running your own GPU inference

## Facets
- artifact type: library
- maturity: active
- function: llm-training, machine-learning, llm-inference
- domain: healthcare, large-language-models, deep-learning
- platform: python
- tags: medical-llm, reasoning, reinforcement-learning, ppo, verifier, fine-tuning, open-weights, natural-language-processing, gpu, linux

## Member repositories
- FreedomIntelligence/HuatuoGPT-o1 (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:27.886530+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:19.690163+00:00, confidence not recorded.
  - readme: https://github.com/FreedomIntelligence/HuatuoGPT-o1 (fetched 2026-08-28T04:04:27.886530+00:00, sha c68f4c6f46cf)
- Data as of 2026-08-30T08:39:29.467469+00:00.