clip : revert the change of BOI/EOI token for GLM-edge (⚠️ breaking change) #13259
Conversation
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
ggerganov
approved these changes
May 2, 2025
|
Look great |
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Outdated suggestions cannot be applied.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 reverts #13081
Ref this discussion #13253 to understand more about this change
The problem was that the embeddings for these BOI/EOI tokens are not present in the text model, hence it was distributed as a separated set of embeddings in vision model.
This also highlights the importance of proper commenting the code, as vision model implementations can be quite different from one to another, and also contain abnormal patches / hacking.
CC @piDack can you have a look?