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:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MCG-NJU/VideoChat3-4B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from MCG-NJU/VideoChat3-4B: direct link, hf CLI and curl.
- Browser
- Download file 133 Bytes
-
https://huggingface.co/MCG-NJU/VideoChat3-4B/resolve/main/processor_config.json
- Command line
-
hf download hf://MCG-NJU/VideoChat3-4B/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/MCG-NJU/VideoChat3-4B/resolve/main/processor_config.json
133 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_videochat3.VideoChat3Processor" | |
| }, | |
| "processor_class": "VideoChat3Processor" | |
| } | |