# D-JEPA: pusht-multi-geometry

- Architecture: `set_aligner`.
- Tensor count: 30.
- Includes pretrained predictor weights: false.
- Original checkpoint SHA256: `d187c0efc194e6faa39007be835f3cca820b16fd95adfb1d7283f3d44d108b56`.
- Exported tensor-file SHA256: `801c92fc312b071fbc43b1e2153ae1ca25c08b1a3ae95110b38c7482e99c0fe3`.

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.

Input width: 388. Gate: `base_minus_refined`, strict threshold `0.027186155319213864`; quantization decimals: `None`. Candidate IDs and feature preprocessing must match the task profile.

Project license is selected by the authors before public upload.