facebookresearch/fairseq
Vedi su GitHubkey_padding_mask is not used in transformer decoder layer?
Open
#537 aperta il 27 feb 2019
bughelp wanted
Metriche repository
- Star
- (29.107 star)
- Metriche merge PR
- (Nessuna PR mergiata in 30 g)
Descrizione
when reading the source code i found that key_padding_mask is not used when calculating self attention. There is no problem when the target is padded right by default because attn_mask could do the same thing. But how about left padding on the target?