Instructions to use pavitemple/video-llava with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pavitemple/video-llava with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pavitemple/video-llava", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from pavitemple/video-llava: direct link, hf CLI and curl.
- Browser
- Download file 167 Bytes
-
https://huggingface.co/pavitemple/video-llava/resolve/main/processor_config.json
- Command line
-
hf download hf://pavitemple/video-llava/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/pavitemple/video-llava/resolve/main/processor_config.json
167 Bytes
| { | |
| "image_token": "<image>", | |
| "patch_size": null, | |
| "processor_class": "VideoLlavaProcessor", | |
| "video_token": "<video>", | |
| "vision_feature_select_strategy": null | |
| } | |