Video-Text-to-Text
Transformers
Safetensors
arc_hunyuan_video
text-generation
multimodal
video-understanding
video-audio understanding
video-qa
video-captioning
video-grounding
video-reasoning
short video understanding
Instructions to use TencentARC/ARC-Hunyuan-Video-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TencentARC/ARC-Hunyuan-Video-7B with Transformers:
# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("TencentARC/ARC-Hunyuan-Video-7B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add model card metadata (pipeline, library, tags) and abstract
#1
by nielsr HF Staff - opened
This PR enhances the model card for ARC-Hunyuan-Video-7B by:
- Adding
pipeline_tag: video-text-to-textto ensure the model is discoverable under the appropriate task filter on the Hugging Face Hub. - Adding
library_name: transformersto indicate compatibility with the Hugging Facetransformerslibrary, allowing users to easily load and use the model with standardtransformersAPI calls. - Adding additional
tags(multimodal,video-understanding,video-qa,video-captioning,audio-understanding) for better categorization and searchability. - Including the paper abstract in a dedicated `
tttoaster changed pull request status to merged