Hi! I'm Niels from the community science team at Hugging Face. I'm opening this PR to improve the model card for Vision-R1-32B.
This update includes:
- Relevant metadata (`pipeline_tag`, `library_name`).
- A description of the model's architecture and training pipeline (Cold-start + RL).
- Performance metrics from the research paper.
- Links to the paper and the official GitHub repository.
- A citation section for the authors' work.
This will help users better understand the model's capabilities and how to use it!
