Visual Document Retrieval
MLX
Safetensors
ColPali
English
colidefics3
colsmol
multi-vector
late-interaction
6-bit
Instructions to use DifferentProductions/colSmol-256M-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use DifferentProductions/colSmol-256M-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download DifferentProductions/colSmol-256M-6bit --local-dir colSmol-256M-6bit
- ColPali
How to use DifferentProductions/colSmol-256M-6bit with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from DifferentProductions/colSmol-256M-6bit: direct link, hf CLI and curl.
- Browser
- Download file 486 Bytes
-
https://huggingface.co/DifferentProductions/colSmol-256M-6bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://DifferentProductions/colSmol-256M-6bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/DifferentProductions/colSmol-256M-6bit/resolve/main/preprocessor_config.json
486 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_image_splitting": true, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Idefics3ImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_image_size": { | |
| "longest_edge": 512 | |
| }, | |
| "processor_class": "Idefics3Processor", | |
| "resample": 1, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 2048 | |
| } | |
| } | |