Instructions to use Hemgg/deepfake_model_Video-MAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hemgg/deepfake_model_Video-MAE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="Hemgg/deepfake_model_Video-MAE")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForVideoClassification processor = AutoImageProcessor.from_pretrained("Hemgg/deepfake_model_Video-MAE") model = AutoModelForVideoClassification.from_pretrained("Hemgg/deepfake_model_Video-MAE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from Hemgg/deepfake_model_Video-MAE: direct link, hf CLI and curl.
- Browser
- Download file 690 MB
-
https://huggingface.co/Hemgg/deepfake_model_Video-MAE/resolve/main/optimizer.pt
- Command line
-
hf download hf://Hemgg/deepfake_model_Video-MAE/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Hemgg/deepfake_model_Video-MAE/resolve/main/optimizer.pt
690 MB
- Xet hash:
- 0756cbe288143ff43b55d39dd3c8a54413d252b9dc1ece72a1065163dcdcf7f1
- Size of remote file:
- 690 MB
- SHA256:
- b18c29a564d7fd9a604ea5f1cda5e47ea89044f8d0bb05e4df4259d2a696dcd8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.