D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models

Authors:
  • HQHaoran Que
    Haoran Que
  • JLJiaheng Liu
    Jiaheng Liu
  • GZGe Zhang
    Ge Zhang
  • CZChenchen Zhang
    Chenchen Zhang
  • XQXingwei Qu
    Xingwei Qu
  • YMYinghao Ma
    Yinghao Ma
  • FDFeiyu Duan
    Feiyu Duan
  • ZBZhiqi Bai
    Zhiqi Bai
  • JWJiakai Wang
    Jiakai Wang
  • YZYuanxing Zhang
    Yuanxing Zhang
  • XTXu Tan
    Xu Tan
  • JFJie Fu
    Jie Fu

Abstract
The world's premier source for conference proceedings, offering Print-on-Demand, DOI, and Content Hosting services.