|
Download pusht-predictive-adaptation/README.md from Shuaijun/D-JEPA: direct link, hf CLI and curl.
- Browser
- Download file 625 Bytes
-
https://huggingface.co/Shuaijun/D-JEPA/resolve/main/pusht-predictive-adaptation/README.md
- Command line
-
hf download hf://Shuaijun/D-JEPA/pusht-predictive-adaptation/README.md
-
curl -L -o README.md https://huggingface.co/Shuaijun/D-JEPA/resolve/main/pusht-predictive-adaptation/README.md
625 Bytes
| # D-JEPA: pusht-predictive-adaptation | |
| - Architecture: `predictor_patch`. | |
| - Tensor count: 22. | |
| - Includes pretrained predictor weights: false. | |
| - Original checkpoint SHA256: `ccbd6ca30c550b60a186c5d0a1fa5f1a43b7a08b704b19037586ff3de52b0887`. | |
| - Exported tensor-file SHA256: `b2bcb7880fb9477a7bb9aaa3c3380b66e4cd5e1767a4093f990c72766ff8e49a`. | |
| Load `model.pt` with `torch.load(..., map_location="cpu", weights_only=True)`. Use the matching D-JEPA code profile and JSON configuration. Tensor values are unchanged; metadata and optimizer state have been separated. | |
| Project license is selected by the authors before public upload. | |