Skip to content
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

align nanollava input with original model #1132

Merged
merged 4 commits into from
Jan 29, 2025

Conversation

eaidova
Copy link
Collaborator

@eaidova eaidova commented Jan 29, 2025

What does this PR do?

nanollava uses images input as input for images in forward and generate, while optimum-intel expects pixel_values. That may lead to difficulties with reusage original model preprocessing.

@eaidova eaidova requested a review from AlexKoff88 January 29, 2025 12:56
@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.

@eaidova
Copy link
Collaborator Author

eaidova commented Jan 29, 2025

failed test is not related, it is sporadic and will be fixed as part of #1133

Copy link
Collaborator

@echarlaix echarlaix left a comment

Choose a reason for hiding this comment

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

LGTM, thanks @eaidova

@echarlaix echarlaix merged commit 68cacea into huggingface:main Jan 29, 2025
21 of 22 checks passed
@eaidova eaidova deleted the ea/nanollava_input branch January 29, 2025 16:58
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.

5 participants