shi-labs

/

slowfast-video-mllm-qwen2-7b-convnext-576-frame64-s1t4

like 0

Follow

SHI Labs 94

Hi Team,

This PR adds a comprehensive model card for the shi-labs/slowfast-video-mllm-qwen2-7b-convnext-576-frame64-s1t4 model, based on the paper Slow-Fast Architecture for Video Multi-Modal Large Language Models.

The model card includes:

• Links to the paper, the official GitHub repository, and the Hugging Face collection.
• Appropriate metadata: pipeline_tag, library_name, tags, and the existing license.
• A description of the Slow-Fast architecture.
• An illustrative figure.
• A sample usage code snippet adapted from the repository, including setup instructions and trust_remote_code=True.
• License details.
• Citation information.

This will make the model more discoverable and easier for the community to understand and use.

Best,
Niels