Specify the head_size from the config when importing Gemma from Hugging Face. #1148
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mfuntowicz
changed the title
|
@mfuntowicz Thanks very much for your great contribution. The changes will be included in the next main branch update to the GitHub, and we will credit you as co-author. Thanks! |
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This fix importing Gemma model from Hugging Face Hub when input and outputs sizes for the attention differs (such as 7b falvour).
The current implementation was inferring the size from the
hidden_sizebut this leads to wrong shape being defined.This PR fixes this by especially setting the
head_sizevalue fromGemmaConfigNeeds PR #1147