transformers
f834d368
- [gemma3] fix bidirectional attention mask (#38080)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
[gemma3] fix bidirectional attention mask (#38080) * fix attn mask * attn viz doesn't show yello cubes between images * bucketize made it hard with different number of crops * fixup
References
#38080 - [gemma3] fix bidirectional attention mask
Author
zucchini-nlp
Parents
2edb0e4b
Loading