Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2502.12671 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929742606761984 |
|---|---|
| author | Wang, Bingning Zhao, Haizhou Zhou, Huozhi Song, Liang Xu, Mingyu Cheng, Wei Zeng, Xiangrong Zhang, Yupeng Huo, Yuqi Wang, Zecheng Zhao, Zhengyun Pan, Da Kou, Fei Li, Fei Chen, Fuzhong Dong, Guosheng Liu, Han Zhang, Hongda He, Jin Yang, Jinjie Wu, Kangxi Wu, Kegeng Su, Lei Niu, Linlin Sun, Linzhuang Wang, Mang Fan, Pengcheng Shen, Qianli Xin, Rihui Dang, Shunya Zhou, Songchi Chen, Weipeng Luo, Wenjing Chen, Xin Men, Xin Lin, Xionghai Dong, Xuezhen Zhang, Yan Duan, Yifei Zhou, Yuyan Ma, Zhi Wu, Zhiying |
| author_facet | Wang, Bingning Zhao, Haizhou Zhou, Huozhi Song, Liang Xu, Mingyu Cheng, Wei Zeng, Xiangrong Zhang, Yupeng Huo, Yuqi Wang, Zecheng Zhao, Zhengyun Pan, Da Kou, Fei Li, Fei Chen, Fuzhong Dong, Guosheng Liu, Han Zhang, Hongda He, Jin Yang, Jinjie Wu, Kangxi Wu, Kegeng Su, Lei Niu, Linlin Sun, Linzhuang Wang, Mang Fan, Pengcheng Shen, Qianli Xin, Rihui Dang, Shunya Zhou, Songchi Chen, Weipeng Luo, Wenjing Chen, Xin Men, Xin Lin, Xionghai Dong, Xuezhen Zhang, Yan Duan, Yifei Zhou, Yuyan Ma, Zhi Wu, Zhiying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Baichuan-M1: Pushing the Medical Capability of Large Language Models Wang, Bingning Zhao, Haizhou Zhou, Huozhi Song, Liang Xu, Mingyu Cheng, Wei Zeng, Xiangrong Zhang, Yupeng Huo, Yuqi Wang, Zecheng Zhao, Zhengyun Pan, Da Kou, Fei Li, Fei Chen, Fuzhong Dong, Guosheng Liu, Han Zhang, Hongda He, Jin Yang, Jinjie Wu, Kangxi Wu, Kegeng Su, Lei Niu, Linlin Sun, Linzhuang Wang, Mang Fan, Pengcheng Shen, Qianli Xin, Rihui Dang, Shunya Zhou, Songchi Chen, Weipeng Luo, Wenjing Chen, Xin Men, Xin Lin, Xionghai Dong, Xuezhen Zhang, Yan Duan, Yifei Zhou, Yuyan Ma, Zhi Wu, Zhiying Computation and Language 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. |
| title | Baichuan-M1: Pushing the Medical Capability of Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.12671 |