Skip to content

[qwen] refactor attentions for vision/audio #38930

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Jun 24, 2025

Conversation

zucchini-nlp
Copy link
Member

What does this PR do?

As per title, these modalities were left out when refactoring VLMs earlier

@zucchini-nlp zucchini-nlp requested a review from Cyrilvallez June 20, 2025 08:22
@HuggingFaceDocBuilderDev

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.

Copy link
Member

@Cyrilvallez Cyrilvallez left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very very much welcome!! 🤗 Main concern is about the kwargs here, they are not flowing correctly in this PR, and I'm not sure if we can flow them all the way in general (e.g., some seqlens passed as kwargs for the language model would clash with those explicitly defined in the other modalities), i.e. does it make sense to have them?

@zucchini-nlp zucchini-nlp merged commit d3d835d into huggingface:main Jun 24, 2025
14 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants