Add a subtle fix for gemma 2 conversions #1701
Merged
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
SamanehSaadat
approved these changes
Jul 19, 2024
There was a problem hiding this comment.
Thanks, Matt!
Just one comment: we may want to update the docstring here since it says Gemma2 always uses hidden_dim/num_query_heads.
Gemma 2 will use different normalization constants for the query depending of the model size. 9b = head_dim 27b = hidden_dim / num_query_heads We need to slightly tweak our config conversion to account for this.
mattdangerw
force-pushed
the
subtle-fix-for-gemma-2-conversion
branch
from
8df5959 to
3e5f3ff
Compare
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Outdated suggestions cannot be applied.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.
Gemma 2 will use different normalization constants for the query depending of the model size.
9b = head_dim
27b = hidden_dim / num_query_heads
We need to slightly tweak our config conversion to account for this.