LibreVJEPA2g384-embed

V-JEPA 2.0 g384 video encoder (clip embedding), converted for LibreYOLO.

from libreyolo import LibreYOLO

model = LibreYOLO("LibreVJEPA2g384-embed.pt")
result = model.predict("clip.mp4")

Source

Converted from facebook/vjepa2-vitg-fpc64-384 at revision 12ca91694b230e0d4b5b0078af6f4ae1d51e933d.

Modifications

The upstream checkpoint is remapped into LibreYOLO's native V-JEPA 2 module and wrapped with LibreYOLO v1.0 checkpoint metadata (family, size, task, dataset variant, clip geometry, preprocessing and the pooling rule). Tensor values are unchanged: the conversion is a key remap, loaded strictly, and the self-supervised predictor tower is dropped as a named, asserted set rather than by substring match.

Parity against unmodified transformers==5.1.0 on float32 CPU is exact (max_abs_diff == 0.0) for both the full final token tensor and the mean-pooled, L2-normalized vector.

Embedding contract

The public embedding is a LibreYOLO pooling contract: the arithmetic mean of the final encoder tokens, L2-normalized. Upstream designates no global retrieval vector, and no retrieval benchmark is claimed for it. The native spatiotemporal token grid is available separately via model.embed_tokens(...).

V-JEPA 2 is trained on video. An image is accepted as a single-frame input, which is a static appearance representation, not a motion one.

License

These weights are Apache-2.0, inherited from the source checkpoint above. The full text is in LICENSE, with attribution in NOTICE. Licences in this family differ per artifact, so do not assume a family-wide licence.