Ricky06662

/

Visurf-7B-NoThink-Best-on-gRefCOCO

like 0

This PR significantly enhances the model card for Ricky06662/Visurf-7B-NoThink-Best-on-gRefCOCO by integrating crucial metadata and comprehensive content.

Key improvements include:

• Metadata:
  • Adding library_name: transformers: Evidence from config.json and the existing usage snippet confirms compatibility with the Hugging Face transformers library, enabling the automated "How to Use" widget.
  • Adding pipeline_tag: image-text-to-text: This accurately categorizes the model as a Vision-Language Model that processes images and text to generate text, improving discoverability on the Hub.
• Content:
  • Explicitly linking to the paper: ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models.
  • Including the full abstract of the paper for quick understanding of the model's approach.
  • Adding a direct link to the official GitHub repository.
  • Incorporating the "Overview" image, "Installation" instructions, and a detailed "Inference" example directly from the GitHub README, including specific example queries and their expected visual outputs.
  • Adding the BibTeX citation from the GitHub repository.

These changes provide a more complete, usable, and discoverable model card for the community.