Open
Conversation
UFO-101
approved these changes
Sep 21, 2024
Owner
UFO-101
left a comment
UFO-101
left a comment
There was a problem hiding this comment.
Hi. Thanks for this PR!
It looks great and correct as far as I can tell. It's a simple enough change that I think tests are not required. But have you used it enough to locally to be fairly confident it hasn't introduced any bugs?
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Minor modifcations to
factorized_dest_nodessuch that models with GroupedQueryAttention (e.g.google/gemma-2-2b) can be loaded. Importantly, the number of query heads does not respond to the number of key and value heads.