[generate] Fix vocab_size access for multimodal models
#37937
Merged
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
… `config.get_text_config().vocab.size` In doing so, we enable multimodal models to fully leverage all existing generation features.
Contributor
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the |
zucchini-nlp
approved these changes
May 5, 2025
Member
zucchini-nlp
left a comment
zucchini-nlp
left a comment
There was a problem hiding this comment.
Thanks, looks good to me! I don't think assisted decoding works with VLMs yet, but oke, let's pass correct vocab size for now
gante
approved these changes
May 5, 2025
Contributor
gante
left a comment
gante
left a comment
There was a problem hiding this comment.
Perfect, thank you for submitting this PR 🤗
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
May 14, 2025
…#37937) Implements last migrations for generation from `config.vocab_size` to `config.get_text_config().vocab.size` In doing so, we enable multimodal models to fully leverage all existing generation features.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #37930
Prior to this PR,
compute_transition_scores,_get_candidate_generatorand_get_logits_processorstill usedconfig.vocab_sizeto access a model's vocab size. This caused issues with multimodal models, as the vocab_size is stored within theirtext_config.This PR addresses this issue by migrating these remaining accesses to
vocab_sizetoconfig.get_text_config().vocab_size.Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@zucchini-nlp @gante