Improve model card: Add pipeline tag, library, paper, GitHub, and usage
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for the Griffon v2 model, aligning it with Hugging Face Hub best practices.
Specifically, it:
- Adds the
pipeline_tag: image-text-to-textto improve discoverability for visual-language tasks. - Specifies
library_name: transformersto indicate compatibility with the Hugging Face Transformers library and enable the "How to use" widget. - Includes a prominent link to the official paper: Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring.
- Provides a direct link to the official GitHub repository: https://github.com/jefferyZhan/Griffon.
- Adds a comprehensive "Quick Start" section with a Python code snippet, demonstrating how to load and use the model with
transformers. - Includes the appropriate BibTeX citation for the Griffon v2 paper.
Please review these improvements.