MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers.
Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, Furu Wei
Browse the full ACL paper archive.
Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, Furu Wei
Browse the full ACL paper archive.