Giters
michaelsdr
/
sinkformers
Transformers with doubly stochastic attention
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
40
Watchers:
2
Issues:
1
Forks:
2
michaelsdr/sinkformers Issues
nice work, did sinkhorn-attention could be applied to casual-language model?
Updated
2 years ago