The current generation of large language models (LLMs) is typically designed for broad, general-purpose applications, while domain-specific LLMs, especially in vertical fields like medicine, remain relatively scarce. In particular, the development of highly efficient and practical LLMs for the medical domain is challenging due to the complexity of medical knowledge and the limited availability of high-quality data. To bridge this gap, we introduce Baichuan-M1, a series of large language models specifically optimized for medical applications. Unlike traditional approaches that simply continue pretraining on existing models or apply post-training to a general base model, Baichuan-M1 is trained from scratch with a dedicated focus on enhancing medical capabilities. Our model is trained on 20 trillion tokens and incorporates a range of effective training methods that strike a balance between general capabilities and medical expertise. As a result, Baichuan-M1 not only performs strongly across general domains such as mathematics and coding but also excels in specialized medical fields. We have open-sourced Baichuan-M1-14B, a mini version of our model, which can be accessed through the following links.
View on arXiv@article{wang2025_2502.12671,
title={ Baichuan-M1: Pushing the Medical Capability of Large Language Models },
author={ Bingning Wang and Haizhou Zhao and Huozhi Zhou and Liang Song and Mingyu Xu and Wei Cheng and Xiangrong Zeng and Yupeng Zhang and Yuqi Huo and Zecheng Wang and Zhengyun Zhao and Da Pan and Fei Kou and Fei Li and Fuzhong Chen and Guosheng Dong and Han Liu and Hongda Zhang and Jin He and Jinjie Yang and Kangxi Wu and Kegeng Wu and Lei Su and Linlin Niu and Linzhuang Sun and Mang Wang and Pengcheng Fan and Qianli Shen and Rihui Xin and Shunya Dang and Songchi Zhou and Weipeng Chen and Wenjing Luo and Xin Chen and Xin Men and Xionghai Lin and Xuezhen Dong and Yan Zhang and Yifei Duan and Yuyan Zhou and Zhi Ma and Zhiying Wu },
journal={arXiv preprint arXiv:2502.12671},
year={ 2025 }
}