DeepGlint-AI

/

mlcd-vit-bigG-patch14-448

like 4

Follow

DeepGlint 31

This PR enhances the model card for mlcd-vit-bigG-patch14-448 by:

• Adding library_name: transformers to the metadata, which enables the "Use in Transformers" widget on the Hub.
• Updating the primary paper reference to Region-based Cluster Discrimination for Visual Representation Learning and including its abstract for better context.
• Adding explicit links to the GitHub repository for the associated codebase.
• Updating the citation section with the correct BibTeX for the RICE paper.
• Introducing relevant tags such as vision-transformer, ocr, object-detection, semantic-segmentation, multimodal-llm, and general-purpose to improve model discoverability based on its capabilities described in the paper abstract.