Instructions to use thoddnn/siglip2-base-patch16-224-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use thoddnn/siglip2-base-patch16-224-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download thoddnn/siglip2-base-patch16-224-8bit --local-dir siglip2-base-patch16-224-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from thoddnn/siglip2-base-patch16-224-8bit: direct link, hf CLI and curl.
- Browser
- Download file 394 Bytes
-
https://huggingface.co/thoddnn/siglip2-base-patch16-224-8bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://thoddnn/siglip2-base-patch16-224-8bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/thoddnn/siglip2-base-patch16-224-8bit/resolve/main/preprocessor_config.json
394 Bytes
| { | |
| "do_convert_rgb": null, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "SiglipImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "SiglipProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| } | |