Video-Text-to-Text
Transformers
Safetensors
English
Chinese
videochat3
feature-extraction
video-language-model
vision-language-model
multimodal
video-understanding
image-understanding
streaming-video
custom_code
Instructions to use MCG-NJU/VideoChat3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MCG-NJU/VideoChat3-4B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MCG-NJU/VideoChat3-4B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_videochat3.VideoChat3Processor" | |
| }, | |
| "processor_class": "VideoChat3Processor" | |
| } | |