Add model card for Chain-of-Frames
#1
by nielsr HF Staff - opened
Hi! I'm opening this pull request to add a model card for this repository.
This model card:
- Links to the paper Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning.
- Adds the
video-text-to-textpipeline tag and thetransformerslibrary name to the metadata. - Provides a link to the official GitHub repository.
- Includes a sample usage section with code for loading the model using the
transformerslibrary, as found in the GitHub README.