Hugging Face's logo

QiWang98
/
VideoRFT

Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
text-generation-inference
Model card Files
xet
 Community
1

Improve model card for VideoRFT with metadata and comprehensive content

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+216
-6
nielsr

This PR significantly improves the model card for VideoRFT by:

  • Updating the pipeline_tag from visual-question-answering to video-text-to-text to accurately reflect the model's capabilities in video reasoning and text generation.
  • Adding library_name: transformers as the model is compatible with the Hugging Face Transformers library, enabling the automated "How to use" widget.
  • Populating the content section with a detailed description, including the paper abstract, methodology, dataset information, installation instructions, training and inference guidance, a runnable Python usage example, and the full citation information.
  • Ensuring direct links to the associated paper and the GitHub repository are prominently displayed.

These enhancements make the model card more informative and user-friendly for the Hugging Face community.
Improve model card for VideoRFT with metadata and comprehensive content933b574c
QiWang98 changed pull request status to merged
nielsr

Hi @QiWang98 could you check the code snippets of the model cards? Looks like those are wrong.

Sign up or log in to comment