Instructions to use danush99/Model_LightOnOCR-Sin-Handwritten-Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use danush99/Model_LightOnOCR-Sin-Handwritten-Text with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("lightonai/LightOnOCR-2-1B") model = PeftModel.from_pretrained(base_model, "danush99/Model_LightOnOCR-Sin-Handwritten-Text") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from danush99/Model_LightOnOCR-Sin-Handwritten-Text: direct link, hf CLI and curl.
- Browser
- Download file 637 Bytes
-
https://huggingface.co/danush99/Model_LightOnOCR-Sin-Handwritten-Text/resolve/main/processor_config.json
- Command line
-
hf download hf://danush99/Model_LightOnOCR-Sin-Handwritten-Text/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/danush99/Model_LightOnOCR-Sin-Handwritten-Text/resolve/main/processor_config.json
637 Bytes
| { | |
| "image_processor": { | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "PixtralImageProcessorFast", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "patch_size": 14, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 1540 | |
| } | |
| }, | |
| "patch_size": 14, | |
| "processor_class": "LightOnOcrProcessor", | |
| "spatial_merge_size": 2 | |
| } | |