Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models.
Bingbing Li, Zigeng Wang, Shaoyi Huang, Mikhail A. Bragin, Ji Li, Caiwen Ding
Browse the full IJCAI paper archive.
Bingbing Li, Zigeng Wang, Shaoyi Huang, Mikhail A. Bragin, Ji Li, Caiwen Ding
Browse the full IJCAI paper archive.