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

[VLM] Multimodal Data Collator #1087

Merged
merged 2 commits into from
Jan 23, 2025
Merged

Conversation

kylesayrs
Copy link
Collaborator

@kylesayrs kylesayrs commented Jan 20, 2025

Purpose

Changes

  • Remove data collator definitions in LC
  • Add data collators in examples with a comment indicating that this is for multimodal inputs

Testing

Ran all multimodal vision models

  • Qwen2
  • Pixtral
  • Mllama
  • Llava
  • Phi3_vision

Copy link

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

@kylesayrs kylesayrs added the ready When a PR is ready for review label Jan 21, 2025
@kylesayrs kylesayrs marked this pull request as ready for review January 21, 2025 04:52
@kylesayrs kylesayrs requested a review from mgoin January 22, 2025 18:19
Copy link
Collaborator

@dsikka dsikka left a comment

Choose a reason for hiding this comment

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

nit about removing empty file otherwise LGTM

@dsikka dsikka merged commit 6377f1e into main Jan 23, 2025
7 of 8 checks passed
@dsikka dsikka deleted the kylesayrs/generalized_data_collator branch January 23, 2025 03:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready When a PR is ready for review
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants