license	datasets	language	base_model	pipeline_tag	tags
apache-2.0	FreedomIntelligence/medical-o1-reasoning-SFT FreedomIntelligence/medical-o1-verifiable-problem	en	meta-llama/Llama-3.1-8B-Instruct	text-generation	medical

HuatuoGPT-o1-8B

GitHub | Paper

Introduction

HuatuoGPT-o1 is a medical LLM designed for advanced medical reasoning. It generates a complex thought process, reflecting and refining its reasoning, before providing a final response.

For more information, visit our GitHub repository: https://github.com/FreedomIntelligence/HuatuoGPT-o1.

Model Info

	Backbone	Supported Languages	Link
HuatuoGPT-o1-8B	LLaMA-3.1-8B	English	HF Link
HuatuoGPT-o1-70B	LLaMA-3.1-70B	English	HF Link
HuatuoGPT-o1-7B	Qwen2.5-7B	English & Chinese	HF Link
HuatuoGPT-o1-72B	Qwen2.5-72B	English & Chinese	HF Link

Usage

You can use HuatuoGPT-o1 in the same way as Llama-3.1-8B-Instruct. You can deploy it with tools like vllm or Sglang, or perform direct inference:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT-o1-8B",torch_dtype="auto",device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/HuatuoGPT-o1-8B")

input_text = "How to stop a cough?"
messages = [{"role": "user", "content": input_text}]

inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False,add_generation_prompt=True
), return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

HuatuoGPT-o1 adopts a thinks-before-it-answers approach, with outputs formatted as:

## Thinking
[Reasoning process]

## Final Response
[Output]

📖 Citation

@misc{chen2024huatuogpto1medicalcomplexreasoning,
      title={HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs}, 
      author={Junying Chen and Zhenyang Cai and Ke Ji and Xidong Wang and Wanlong Liu and Rongsheng Wang and Jianye Hou and Benyou Wang},
      year={2024},
      eprint={2412.18925},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.18925}, 
}