craigwu

/

visual_jigsaw_image_7B

like 1

This PR adds a model card for the Visual Jigsaw model, linking it to the paper Visual Jigsaw Post-Training Improves MLLMs.

The update includes:

• Adding the license: apache-2.0.
• Setting the pipeline_tag: image-text-to-text.
• Adding library_name: transformers as the model is compatible with the library.
• Including a direct link to the project page and the GitHub repository.
• A brief description of the model.

This will improve discoverability and provide essential information for users.