Finemedlm O1

🚀 FineMedLM-o1

FineMedLM-o1 is a specialized medical large language model (LLM) designed for advanced medical reasoning. It uses a multi - step reasoning process, iteratively reflecting on and refining its thought process before giving a final response.

🚀 Quick Start

You can use FineMedLM-o1 in the same way as Llama-3.1-8B-Instruct. Here is a code example to show you how to use it:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("hongzhouyu/FineMedLM-o1")
tokenizer = AutoTokenizer.from_pretrained("hongzhouyu/FineMedLM-o1")

prompt = "How do the interactions between neuronal activity, gonadal hormones, and neurotrophins influence axon regeneration post-injury, and what are the potential therapeutic implications of this research? Please think step by step."
messages = [
    {"role": "system", "content": "You are a helpful professional doctor."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt")

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)

FineMedLM-o1 adopts a slow - thinking approach, with outputs formatted as:

**Thought**
[Reasoning process]

**Summarization**
[Output]

📚 Documentation

Model Information

Links

• GitHub
• Paper

📄 License

This project is licensed under the MIT license.

📚 Citation

If you use this model in your research, please cite the following paper:

@misc{yu2025finemedlmo1enhancingmedicalreasoning,
    title={FineMedLM-o1: Enhancing the Medical Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training}, 
    author={Hongzhou Yu and Tianhao Cheng and Ying Cheng and Rui Feng},
    year={2025},
    eprint={2501.09213},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2501.09213}, 
}