V JEPA2 Vitl Fpc16 256 Ssv2
Apple MLX fp16 port of facebook/vjepa2-vitl-fpc16-256-ssv2 — V-JEPA2 ViT-L encoder + attentive-pooler + linear head for Something-Something-v2 action recognition (174 classes). MIT.
Model source
- Kind
- Other
- File size
- 674 MB
- Version
- vRevision 3669d14
- Updated
- Oct 11, 2026
- Downloads
- 15
- Source
- Hugging Face
Source description
V-JEPA2 ViT-L SSv2 classifier (MLX)
Apple MLX fp16 port of facebook/vjepa2-vitl-fpc16-256-ssv2 — V-JEPA2 ViT-L
encoder + attentive-pooler + linear head for Something-Something-v2 action
recognition (174 classes). MIT.
pip install vjepa2-mlx # https://github.com/xocialize/vjepa2-mlx
vjepa2-mlx -i clip.mp4 --task classify
- Parity vs PyTorch (cpu fp32): logits rel 2.43e-6, argmax matches (fp16 too).
- Precision: fp16 (~707 MB).
MIT (© Meta Platforms).
Sources
1 source
Sources
1 sourceVerified Oct 11
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: mit library_name: mlx pipeline_tag: video-classification tags: [mlx, video, vjepa2, video-classification, something-something-v2, apple-silicon] --- # V-JEPA2 ViT-L SSv2 classifier (MLX) Apple **MLX** fp16 port of `facebook/vjepa2-vitl-fpc16-256-ssv2` — V-JEPA2 ViT-L encoder + attentive-pooler + linear head for **Something-Something-v2** action recognition (174 classes). MIT. ```bash pip install vjepa2-mlx # https://github.com/xocialize/vjepa2-mlx vjepa2-mlx -i clip.mp4 --task classify ``` - **Parity vs PyTorch (cpu fp32)**: logits rel 2.43e-6, argmax matches (fp16 too). - **Precision**: fp16 (~707 MB). MIT (© Meta Platforms).
Source context: 15 downloads · 1 likes · Pipeline video-classification · Library mlx · Repo mlx-community/V-JEPA2-vitl-fpc16-256-ssv2
Source context: 18 downloads · 1 likes · Pipeline video-classification · Library mlx · Repo mlx-community/V-JEPA2-vitl-fpc16-256-ssv2
