Instructions to use vikp/surya_order with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikp/surya_order with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("vikp/surya_order") model = AutoModel.from_pretrained("vikp/surya_order", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from vikp/surya_order: direct link, hf CLI and curl.
- Browser
- Download file 684 Bytes
-
https://huggingface.co/vikp/surya_order/resolve/7b727d0a2c942cdc8596d186115f65c12c812bd8/preprocessor_config.json
- Command line
-
hf download hf://vikp/surya_order@7b727d0a2c942cdc8596d186115f65c12c812bd8/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/vikp/surya_order/resolve/7b727d0a2c942cdc8596d186115f65c12c812bd8/preprocessor_config.json
684 Bytes
| { | |
| "box_pad_id": 1001, | |
| "box_size": { | |
| "height": 1024, | |
| "width": 1024 | |
| }, | |
| "do_align_long_axis": false, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_reduce_labels": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_thumbnail": true, | |
| "feature_extractor_type": "SegformerFeatureExtractor", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "OrderImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "max_boxes": 255, | |
| "patch_size": [ | |
| 4, | |
| 4 | |
| ], | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 1024, | |
| "width": 1024 | |
| }, | |
| "token_pad_id": 1282, | |
| "token_sep_id": 1281 | |
| } | |