Safetensors
qwen2_5_vl

Improve model card: Add pipeline tag, library name, abstract, and comprehensive details

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card for qunwang13/vr-thinker by:

  • Adding pipeline_tag: video-text-to-text for improved discoverability, as the model handles video input and text output for reward modeling.
  • Including library_name: transformers, as the provided sample usage clearly demonstrates compatibility with the Hugging Face Transformers library.
  • Updating the paper link to the official Hugging Face paper page: https://huggingface.co/papers/2510.10518.
  • Incorporating the full abstract from the paper to provide a comprehensive overview of the model.
  • Adding detailed sections such as "Overview," "Training Pipeline," "Results," and "Acknowledgement" directly from the GitHub README, including updated image links, to provide a richer understanding of the model's design, training, and performance.
  • Preserving the existing "Quick Start" usage code snippet to maintain usability.
Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment