Instructions to use vikp/surya_rec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikp/surya_rec with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("vikp/surya_rec") model = AutoModel.from_pretrained("vikp/surya_rec", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from vikp/surya_rec: direct link, hf CLI and curl.
- Browser
- Download file 608 Bytes
-
https://huggingface.co/vikp/surya_rec/resolve/refs%2Fpr%2F2/preprocessor_config.json
- Command line
-
hf download hf://vikp/surya_rec@refs/pr/2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/vikp/surya_rec/resolve/refs%2Fpr%2F2/preprocessor_config.json
608 Bytes
| { | |
| "do_align_long_axis": true, | |
| "do_normalize": false, | |
| "do_pad": false, | |
| "do_rescale": false, | |
| "do_resize": false, | |
| "do_thumbnail": false, | |
| "feature_extractor_type": "DonutFeatureExtractor", | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "SuryaImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_size": { | |
| "height": 196, | |
| "width": 896 | |
| }, | |
| "patch_size": [ | |
| 4, | |
| 4 | |
| ], | |
| "processor_class": "SuryaProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 2560, | |
| "width": 1920 | |
| }, | |
| "train": true | |
| } | |