antgroup

/

HumanSense_Omni_Reasoning

like 2

Follow

Ant Group 25

This PR improves the model card for HumanSense_Omni_Reasoning by:

• Updating the pipeline_tag from visual-question-answering to video-text-to-text to better reflect the model's multimodal input (video + text) and text output capabilities. This ensures the model is discoverable under the appropriate pipeline at https://huggingface.co/models?pipeline_tag=video-text-to-text.
• Adding library_name: transformers to the metadata, enabling an interactive "how to use" widget directly on the model page with a functional code snippet.