Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training 文章

ArXiv CS.CL2026-06-05NEWSen作者: Yongwei Zhou, Juncheng Diao, Junlin Shang, Peiguang Li, Rongxiang Weng

Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training · 相关人物

暂无数据