Instructions to use phonsobon/text_extraction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use phonsobon/text_extraction with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("phonsobon/text_extraction", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from phonsobon/text_extraction: direct link, hf CLI and curl.
- Browser
- Download file 432 Bytes
-
https://huggingface.co/phonsobon/text_extraction/resolve/main/processor_config.json
- Command line
-
hf download hf://phonsobon/text_extraction/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/phonsobon/text_extraction/resolve/main/processor_config.json
432 Bytes
| { | |
| "add_reasoning_tokens": false, | |
| "apply_augments": true, | |
| "bbox_size": 1024, | |
| "beacon_token_interval": 512, | |
| "blank_bbox_token_id": 1025, | |
| "merge_size": 2, | |
| "num_beacon_tokens": 4, | |
| "num_register_tokens": 4, | |
| "patch_size": 14, | |
| "processor_class": "MultimodalFoundationProcessor", | |
| "styles": [ | |
| "Plain", | |
| "Handwriting", | |
| "Math", | |
| "Chemical", | |
| "Code" | |
| ], | |
| "use_script_tokens": true | |
| } | |