add learned padding tokens, same strategy as dalle1, for diffusion prior, and get rid of masking in causal transformer

This commit is contained in:
Phil Wang
2022-07-12 17:33:14 -07:00
parent cd26c6b17d
commit 3ee3c56d2a
3 changed files with 31 additions and 15 deletions

View File

@@ -1 +1 @@
__version__ = '0.22.3'
__version__ = '0.23.1'