Improve model card: add paper info, repository link, and description
#1
by
nielsr
HF Staff
- opened
This PR improves the model card for VTC-R1-Glyph. Key changes include:
- Added a link to the paper: VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning.
- Added a link to the official GitHub repository.
- Updated metadata with the correct
pipeline_tag: image-text-to-text. - Provided a model description explaining the VTC-R1 "optical memory" paradigm.
- Included setup instructions for inference.
- Organized existing training hyperparameters.