Instructions to use vasanth009/vjepa2-vitg-fpc64-256-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use vasanth009/vjepa2-vitg-fpc64-256-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir vjepa2-vitg-fpc64-256-mlx vasanth009/vjepa2-vitg-fpc64-256-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "hidden_size": 1408, | |
| "num_hidden_layers": 40, | |
| "num_attention_heads": 22, | |
| "mlp_ratio": 4.363636363636363, | |
| "patch_size": 16, | |
| "tubelet_size": 2, | |
| "crop_size": 256, | |
| "frames_per_clip": 64, | |
| "in_chans": 3, | |
| "hidden_act": "gelu", | |
| "layer_norm_eps": 1e-06, | |
| "qkv_bias": true, | |
| "pred_hidden_size": 384, | |
| "pred_num_hidden_layers": 12, | |
| "pred_num_attention_heads": 12, | |
| "pred_mlp_ratio": 4.0, | |
| "pred_num_mask_tokens": 10, | |
| "num_pooler_layers": 3, | |
| "num_labels": 174, | |
| "hf_repo": "facebook/vjepa2-vitg-fpc64-256" | |
| } |