m1-7B-1K

<div align="center"> <h1> <b>m1</b>: Unleash the Potential of Test-Time Scaling for Medical Reasoning in Large Language Models </h1> <p> A simple test-time scaling strategy, with minimal fine-tuning, can unlock strong medical reasoning within large language models. </p> </div>

Paper: https://arxiv.org/abs/2504.00869

⚡ Introduction

Hi! Welcome to the repository for m1!

m1 is a medical LLM designed to enhance reasoning through efficient test-time scaling. It enables lightweight models to match or exceed the performance of much larger counterparts by extending inference-time “thinking.” Unlike methods that rely on complex RL or expert supervision, m1 achieves strong results through:

• Fine-tuning on a small, high-quality set of verified medical reasoning examples, showing that even with just 1K–23K examples, m1-7B surpasses previous SOTA models like HuatuoGPT-o1-7B and UltraMedical-8B, and m1-32B rivals 70B-scale models.

• Scaling reasoning at inference using token budgets, which consistently improves performance across medical QA tasks: up to an optimal ~4K token budget, beyond which performance may degrade due to overthinking.

• Identifying medical knowledge as the key bottleneck, revealing that additional reasoning alone cannot overcome knowledge gaps; instead, improvements require better data quality and increased model capacity.

🏃 Inference

m1 can be used just like Qwen2.5-7b-Instruct. You can deploy it with tools like vllm or Sglang, or perform direct inference (example provided in the README). See the Github repository for details and examples.

📖 Citation

@misc{huang2025m1UnleashPotential,
      title={m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning in Large Language Models}, 
      author={Xiaoke Huang and Juncheng Wu and Hui Liu and Xianfeng Tang and Yuyin Zhou},
      year={2025},
      eprint={2504.00869},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2504.00869}, 
}