Instructions to use mlx-community/sam3-mxfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/sam3-mxfp4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/sam3-mxfp4 --local-dir sam3-mxfp4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download processor_config.json from mlx-community/sam3-mxfp4: direct link, hf CLI and curl.
- Browser
- Download file 436 Bytes
-
https://huggingface.co/mlx-community/sam3-mxfp4/resolve/main/processor_config.json
- Command line
-
hf download hf://mlx-community/sam3-mxfp4/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/mlx-community/sam3-mxfp4/resolve/main/processor_config.json
436 Bytes
| { | |
| "processor_class": "Sam3Processor", | |
| "image_processor": { | |
| "image_processor_type": "Sam3ImageProcessor", | |
| "size": { | |
| "height": 1008, | |
| "width": 1008 | |
| }, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "do_resize": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "rescale_factor": 0.00392156862745098 | |
| }, | |
| "target_size": 1008 | |
| } |