shi-labs

/

slowfast-video-mllm-qwen2-7b-convnext-576-frame96-s1t6

like 0

Follow

SHI Labs 63

This PR adds a model card for the paper Slow-Fast Architecture for Video Multi-Modal Large Language Models.

It includes:

• A link to the paper.
• A link to the code repository.
• Metadata for the license, library name (transformers), and pipeline tag (video-text-to-text) to improve discoverability.
• Sample usage code.