BleachNick

/

Mentor

like 0

This PR adds a comprehensive model card for the MENTOR model, based on the paper MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models.

The model card includes:

• Relevant metadata: pipeline_tag: text-to-image, library_name: transformers, and license: mit.
• Links to the paper, project page, and GitHub repository.
• An overview, key features, main results, and a usage example to help users understand and get started with the model.

Please review and merge this PR.