Downloads · 30 days
0
vjepa2-vitl
lucid-dl/vjepa2-vitl
vjepa2-vitl is a video classification model from lucid-dl. Use it for the video classification task on the model card, and read the license before you ship it in a product. It is set up for lucid. The card lists the license as mit.
Access
Public
Updated Sep 20, 2026
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.5 GB · 100%
At a glance
- Task
- Video Classification
- Library
- lucid
- License
- mit
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026
- SHA
- 6d9e328a
Model card
From the Hugging Face model README
V-JEPA 2 ViT-L/16
Lucid port of facebook/vjepa2-vitl-fpc64-256/model.safetensors,
converted to Lucid-native safetensors.
Available weights
| Tag | Params | GFLOPs | Size | Source |
|---|---|---|---|---|
FPC64_256 (default) | 326.0M | — | 2402.79 MB |
Usage
import lucid.models as models
from lucid.models.weights import Vjepa2VitLargeWeights
# default tag
model = models.vjepa2_vit_large(pretrained=True)
# explicit tag (enum or string)
model = models.vjepa2_vit_large(weights=Vjepa2VitLargeWeights.FPC64_256)
model = models.vjepa2_vit_large(pretrained="FPC64_256")
# preprocessing travels with the weights
weights = Vjepa2VitLargeWeights.FPC64_256
preprocess = weights.transforms()
out = model(preprocess(image)[None])
logits = out.logits # (B, num_classes)
Conversion
Converted from facebook/vjepa2-vitl-fpc64-256/model.safetensors via
python -m tools.convert_weights vjepa2_vit_large --tag FPC64_256.
Key mapping + numerical parity verified against the source.
License
mit — inherited from the original weights.
Citation
Assran et al., "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning," arXiv:2506.09985, 2025.
- Task
- Video Classification
- Library
- lucid
- License
- mit
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026