Hugging Face's logo

AVoCaDO-Captioner
/
AVoCaDO

Safetensors
qwen2_5_omni
audiovisual
video
captioner
Model card Files
xet
Community
1

Improve model card: Add pipeline tag, library name, and complete citation

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+10
-3
nielsr

This PR enhances the model card for AVoCaDO by:

  • Adding pipeline_tag: video-text-to-text to improve discoverability on the Hub, accurately reflecting the model's functionality of generating text descriptions from video input.
  • Specifying library_name: transformers in the metadata, as evidence from config.json ("transformers_version": "4.52.4" and Qwen2_5OmniForConditionalGeneration architecture) confirms compatibility with the Hugging Face Transformers library, enabling an automated usage widget.
  • Completing the Citation section with the appropriate BibTeX entry for the paper.

These updates provide more comprehensive information for users and integrate the model more effectively within the Hugging Face ecosystem.

 Improve model card: Add pipeline tag, library name, and complete citation3bdfde14
Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment