Instructions to use mnmly/anycalib-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mnmly/anycalib-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir anycalib-mlx mnmly/anycalib-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "architecture": "anycalib", | |
| "backbone": "dinov2_vitl14", | |
| "embed_dim": 1024, | |
| "depth": 24, | |
| "num_heads": 16, | |
| "patch_size": 14, | |
| "out_index": [ | |
| 4, | |
| 11, | |
| 17, | |
| 23 | |
| ], | |
| "norm_layer": false, | |
| "decoder_dim_dhat": 256, | |
| "up_factor": 7, | |
| "resolution": 102400, | |
| "edge_divisible_by": 14, | |
| "ar_range": [ | |
| 0.5, | |
| 2.0 | |
| ], | |
| "dtype": "float32", | |
| "source_checkpoint": "anycalib_edit.pt" | |
| } | |