Instructions to use nativ-community/MiniCPM-OCR-1.0-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nativ-community/MiniCPM-OCR-1.0-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download nativ-community/MiniCPM-OCR-1.0-4bit --local-dir MiniCPM-OCR-1.0-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from nativ-community/MiniCPM-OCR-1.0-4bit: direct link, hf CLI and curl.
- Browser
- Download file 374 Bytes
-
https://huggingface.co/nativ-community/MiniCPM-OCR-1.0-4bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://nativ-community/MiniCPM-OCR-1.0-4bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/nativ-community/MiniCPM-OCR-1.0-4bit/resolve/main/preprocessor_config.json
374 Bytes
| { | |
| "max_slice_nums": 9, | |
| "scale_resolution": 448, | |
| "patch_size": 14, | |
| "use_image_id": true, | |
| "slice_mode": true, | |
| "downsample_mode": "4x", | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "MiniCPMOcrImageProcessor", | |
| "processor_class": "MiniCPMOcrProcessor", | |
| "adaptive_tile_upsize": false | |
| } | |