• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Mixture of Attention Heads: Selecting Attention Heads Per Token.

Xiaofeng ZhangYikang ShenZeyu HuangJie ZhouWenge RongZhang Xiong
Published in: CoRR (2022)
Keyphrases