Skip to content

Conversation

@szabadka
Copy link
Collaborator

@szabadka szabadka commented Apr 4, 2024

In the generation code we were feeding the last token of the prompt twice through the transformer. The new version fixes that and also works in the case where Prefill is completely disabled.

In the generation code we were feeding the last token of the prompt
twice through the transformer. The new version fixes that and also
works in the case where Prefill is completely disabled.
@jan-wassenberg jan-wassenberg added the copybara-import Trigger Copybara for merging pull requests label Apr 4, 2024
@copybara-service copybara-service bot merged commit 08948f1 into google:dev Apr 4, 2024
@szabadka szabadka deleted the gemma3 branch April 24, 2024 09:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

copybara-import Trigger Copybara for merging pull requests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants