dgrauet/vjepa-2.1-vitl-mlx

MLX format model.

Converted with mlx-forge.

Usage

These weights can be used with vjepa2-mlx:

git clone https://github.com/dgrauet/vjepa2-mlx.git && cd vjepa2-mlx
uv pip install -e packages/vjepa2-core-mlx

python - <<'PY'
from vjepa2_core_mlx.utils.weights import from_pretrained

encoder = from_pretrained("dgrauet/vjepa-2.1-vitl-mlx")   # or a local converted directory
feats = encoder(clip)                    # clip: B, C, T, H, W (channels-first)
PY

Related Projects

• Upstream (Meta): https://github.com/facebookresearch/vjepa2
• MLX inference port: https://github.com/dgrauet/vjepa2-mlx
• Source checkpoint: https://dl.fbaipublicfiles.com/vjepa2/vjepa2_1_vitl_dist_vitG_384.pt

Files

• config.json (861.00 B)
• encoder.safetensors (1.14 GB)
• predictor.safetensors (87.65 MB)
• split_model.json (944.00 B)