Hi! I'm Niels from the Hugging Face community team.
This PR adds a comprehensive model card for **OCRVerse**. It includes:
- Relevant metadata: `pipeline_tag`, `library_name`, and `license`.
- A link to the paper: [OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models](https://huggingface.co/papers/2601.21639).
- A link to the official GitHub repository: [https://github.com/DocTron-hub/OCRVerse](https://github.com/DocTron-hub/OCRVerse).
- Sample usage code for both text-centric and vision-centric OCR tasks, directly derived from the official GitHub README.
Please review and merge if this looks good to you!
