DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

作者：DeepSeek-AI Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, C. Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, Huazuo Gao, Kaige Gao, Wenjun Gao, Ruiqi Ge, Kang Guan, Daya Guo, Jianzhong Guo, Guangbo Hao, Zhewen Hao, Ying He, Wen-Hui Hu, Panpan Huang, Erhang Li, Guowei Li, Jiashi Li, Yao Li, Y. K. Li, W. Liang, Fangyun Lin, A. Liu, Bo Liu, Wen Liu, Xiaodong Liu, Xin Liu, Yiyuan Liu, Haoyu Lu, Shanghao Lu, Fuli Luo, Shirong Ma, X. Nie, Tian Pei, Y. Piao, Junjie Qiu, Hui Qu, Tongzheng Ren, Z. Ren, C. Ruan, Zhangli Sha, Zhihong Shao, Jun-Mei Song, Xuecheng Su, Jingxiang Sun, Yaofeng Sun, M. Tang, Bing-Li Wang, Peiyi Wang, Shiyu Wang, Yaohui Wang, Yongji Wang, Tong Wu, Yu Wu, Xin Xie, Zhenda Xie, Ziwei Xie, Yi Xiong, Hanwei Xu, R. X. Xu, Yanhong Xu, Dejian Yang, Yu-mei You, Shuiping Yu, Xin-yuan Yu, Bo Zhang, Haowei Zhang, Lecong Zhang, Liyue Zhang, Mingchuan Zhang, Minghu Zhang, Wentao Zhang, Yichao Zhang, Chenggang Zhao, Yao Zhao, Shangyan Zhou, Shunfeng Zhou, Qihao Zhu, Yuheng Zou · 发表于：arXiv.org · 年份：2024 · 被引用次数：829 · 研究领域：Computer Science

The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions, which casts a dark cloud over scaling LLMs. We delve into the study of scaling laws and present our distinctive findings that facilitate scaling of large scale models in two commonly used open-source configurations, 7B and 67B. Guided by the scaling laws, we introduce DeepSeek LLM, a project dedicated to advancing open-source language models with a long-term perspective. To support the pre-training phase, we have developed a dataset that currently consists of 2 trillion tokens and is continuously expanding. We further conduct supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) on DeepSeek LLM Base models, resulting in the creation of DeepSeek Chat models. Our evaluation results demonstrate that DeepSeek LLM 67B surpasses LLaMA-2 70B on various benchmarks, particularly in the domains of code, mathematics, and reasoning. Furthermore, open-ended evaluations reveal that DeepSeek LLM 67B Chat exhibits superior performance compared to GPT-3.5.