Instructions to use Rickkosse/florence2-docvqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rickkosse/florence2-docvqa with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Rickkosse/florence2-docvqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Rickkosse/florence2-docvqa: direct link, hf CLI and curl.
- Browser
- Download file 633 Bytes
-
https://huggingface.co/Rickkosse/florence2-docvqa/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Rickkosse/florence2-docvqa/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Rickkosse/florence2-docvqa/resolve/main/preprocessor_config.json
633 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "microsoft/Florence-2-base-ft--processing_florence2.Florence2Processor" | |
| }, | |
| "crop_size": { | |
| "height": 768, | |
| "width": 768 | |
| }, | |
| "do_center_crop": false, | |
| "do_convert_rgb": null, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "CLIPImageProcessor", | |
| "image_seq_length": 577, | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "processor_class": "Florence2Processor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 768, | |
| "width": 768 | |
| } | |
| } | |