---
license: mit
library_name: transformers
pipeline_tag: question-answering
---

<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>

## ⚡ Introduction

![](assets/teaser.png)

Hi! Welcome to the repository for **m1** (📃 [Paper](https://arxiv.org/abs/2504.00869))!

**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.

We open-sourced our models, data, and code here.



****************************************************************

**Updates:**

* 2025-03: We release our code, data, models, and paper!

****************************************************************

### 🌍 Environment

Please refer to [docs/ENV.md](docs/ENV.md).

### 👨‍⚕️ Models and Data

| Model            | Backbone              | Training Data                                                                 | Link                                                           |
| ---------------- | --------------------- | ----------------------------------------------------------------------------- | -------------------------------------------------------------- |
| **m1-32b-1k**     | Qwen2.5-32B-Instruct  | [m1k](https://huggingface.co/datasets/UCSC-VLAA/m1k-tokenized)                | [HF Link](https://huggingface.co/UCSC-VLAA/m1-32B-1K)          |
| **m1-7b-1k**      | Qwen2.5-7B-Instruct   | [m1k](https://huggingface.co/datasets/UCSC-VLAA/m1k-tokenized)                | [HF Link](https://huggingface.co/UCSC-VLAA/m1-7B-1K)           |
| **m1-7b-23k**     | Qwen2.5-7B-Instruct   | [m23k](https://huggingface.co/datasets/UCSC-VLAA/m23k-tokenized)              | [HF Link](https://huggingface.co/UCSC-VLAA/m1-7B-23K)          |


### 🏃 Inference

(... same content as original README ...)

### 📖 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}, 
}
```