Ricky06662

/

Visurf-7B-Best-on-gRefCOCO

like 0

This PR significantly enhances the model card for the Visurf-7B-Best-on-gRefCOCO model by:

• Adding library_name: transformers to enable automated code snippets for the Hugging Face transformers library, as evidenced by the existing usage example and config.json.
• Adding pipeline_tag: image-text-to-text for better model discoverability on the Hugging Face Hub, reflecting its nature as a Large Vision-and-Language Model.
• Including a link to the paper: ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models.
• Adding a link to the official GitHub repository for code and further resources: https://github.com/dvlab-research/ViSurf.
• Populating the model card with a comprehensive overview (including the abstract and diagram), detailed installation instructions, inference examples, evaluation, training guidelines, and other relevant information directly from the project's GitHub README. This provides a rich and user-friendly documentation for the model.

Please review these additions and merge this PR.