Task
Video Classification
V
facebook/vjepa2-vitg-fpc64-256
Video Classification·facebook· 141.6K· 56
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository.
# pull & run locally
pip install mlforge-sdk && mlforge pull facebook/vjepa2-vitg-fpc64-256
pip install mlforge-sdk && mlforge pull facebook/vjepa2-vitg-fpc64-256
Model details
Provider
facebook
Framework
transformers
Parameters
1.0B
Size
19 GB
License
apache-2.0
Downloads
141.6K
Likes
56
Updated
2025-08-11
About facebook/vjepa2-vitg-fpc64-256
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository.