# LeVJEPA
LeVJEPA produces clip embeddings and spatial patch tokens from video.
Tasks: Embeddings. Install: pip install libreyolo.
Verified against LibreYOLO v1.6.0.

## Install

```bash
pip install "libreyolo"
```

## Predict

**Python**

```python
from libreyolo import LibreYOLO, SAMPLE_IMAGE

model = LibreYOLO("LibreLeVJEPAl-embed.pt", device="cpu")
result = model(SAMPLE_IMAGE)
print(result.embeddings)
print(model.embed_tokens(SAMPLE_IMAGE).shape)
```

The encoder uses 16 frames at 224 pixels. Finite videos use a centered window sampled at approximately 7.5 FPS. `embed_tokens()` exposes patch tokens. Training is not supported. The TorchScript graph requires direct clip input with batch 1. Pretrained weights are CC-BY-NC-4.0.

## Export

| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | ncnn | TFLite | CoreML | Core AI |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Embeddings | yes | yes | yes | yes | yes |  |  |  |  |  |  |  |

A "yes" means the export is supported. An empty cell means the exporter refuses that combination.

**Python**

```python
from libreyolo import LibreYOLO, SAMPLE_IMAGE

model = LibreYOLO("LibreLeVJEPAl-embed.pt", device="cpu")
model.export(format="onnx")
```

[Export setup](/docs/export) lists format dependencies and loading exported artifacts.

## Checkpoints

| File | Input (px) | Task | Weights license |
| --- | --- | --- | --- |
| `LibreLeVJEPAl-embed.pt` |  | Embeddings | cc-by-nc-4.0 |

## Licensing

Check the license on the Hugging Face repository of the specific weights you download. That repository is authoritative and licenses are not always uniform across a family. This is a description of the licenses involved, not legal advice.

- Original work: LeVJEPA, MLO Lab
- Upstream license: MIT code; CC-BY-NC-4.0 weights
- Upstream source: https://github.com/MLO-lab/LeVJEPA
- LibreYOLO code: MIT
- Weights: MIT code; CC-BY-NC-4.0 weights, republished at https://huggingface.co/LibreYOLO
- Interpretation: The repository declares an explicit CC-BY-NC-4.0 exception for pretrained weights. Commercial use of those weights is excluded.

## Citation

```bibtex
@misc{kuhn2026levjepaefficientscalable,
      title={LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics}, 
      author={Lukas Kuhn and Lucas Maes and Giuseppe Serra and Quentin Le Lidec and Yann LeCun and Randall Balestriero and Florian Buettner},
      year={2026},
      eprint={2608.27395},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.27395}, 
}
```

Copied from https://raw.githubusercontent.com/MLO-lab/LeVJEPA/main/README.md