Instructions to use Tommidi/st_vit_pretrained-1epoch-ucf101 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tommidi/st_vit_pretrained-1epoch-ucf101 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import ST_Vit model = ST_Vit.from_pretrained("Tommidi/st_vit_pretrained-1epoch-ucf101", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Tommidi/st_vit_pretrained-1epoch-ucf101: direct link, hf CLI and curl.
- Browser
- Download file 385 Bytes
-
https://huggingface.co/Tommidi/st_vit_pretrained-1epoch-ucf101/resolve/main/config.json
- Command line
-
hf download hf://Tommidi/st_vit_pretrained-1epoch-ucf101/config.json
-
curl -L -o config.json https://huggingface.co/Tommidi/st_vit_pretrained-1epoch-ucf101/resolve/main/config.json
385 Bytes
| { | |
| "_name_or_path": "Tommidi/st_vit_untrained-101", | |
| "architectures": [ | |
| "ST_Vit" | |
| ], | |
| "model_type": "st_vit", | |
| "out_channels": 101, | |
| "spatial_vit": { | |
| "model_type": "vit" | |
| }, | |
| "temporal_vit": { | |
| "model_type": "vit" | |
| }, | |
| "temporal_vit_mae": { | |
| "model_type": "vit_mae", | |
| "out_channels": 101 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2" | |
| } | |