参考学习资料 AI人工智能 NorMuon_ Making Muon more efficient and scalable__.pdfVIP

  • 1
  • 0
  • 约5.83万字
  • 约 19页
  • 2026-08-19 发布于广西
  • 举报

参考学习资料 AI人工智能 NorMuon_ Making Muon more efficient and scalable__.pdf

NorMuon:MakingMuonmoreefficientandscalable

∗1∗1†221

ZichongLi,LimingLiu,ChenLiang,WeizhuChen,TuoZhao

1GeorgiaTech2Microsoft

5Abstract

2

0Thechoiceofoptimizersignificantlyimpactsthetrainingefficiencyandcomputationalcosts

2oflargelanguagemodels(LLMs).

文档评论(0)

1亿VIP精品文档

相关文档