Instructions to use nvidia/RADIO-L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/RADIO-L with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="nvidia/RADIO-L", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/RADIO-L", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from nvidia/RADIO-L: direct link, hf CLI and curl.
- Browser
- Download file 331 Bytes
-
https://huggingface.co/nvidia/RADIO-L/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://nvidia/RADIO-L/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/nvidia/RADIO-L/resolve/main/preprocessor_config.json
331 Bytes
| { | |
| "crop_size": { | |
| "height": 768, | |
| "width": 768 | |
| }, | |
| "do_center_crop": false, | |
| "do_convert_rgb": true, | |
| "do_normalize": false, | |
| "do_rescale": true, | |
| "do_resize": false, | |
| "image_processor_type": "CLIPImageProcessor", | |
| "processor_class": "CLIPProcessor", | |
| "resample": 3, | |
| "size": { | |
| "shortest_edge": 768 | |
| } | |
| } |