Conversation
Contributor
|
I think is #126 is more robust because it aligns after analyzing the mismatch rather than always truncating, so that it isn't just a fix for Gemma 3, but for other models with their own niche vocabulary problems. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Gemma 3 tokenizer has an inconsistency between the
vocab_sizevalue (262144) and the size of thevocabdictionary (262145)It has a special token called <image_soft_token> of token id 262144 and this token is part of the vocab dictionary from
tokenizer.get_vocab()but is not counted into the vocab size.