Instructions to use m4dma8/dinov3-convnext-balanced_finalrun with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use m4dma8/dinov3-convnext-balanced_finalrun with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="m4dma8/dinov3-convnext-balanced_finalrun")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("m4dma8/dinov3-convnext-balanced_finalrun") model = AutoModel.from_pretrained("m4dma8/dinov3-convnext-balanced_finalrun", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from m4dma8/dinov3-convnext-balanced_finalrun: direct link, hf CLI and curl.
- Browser
- Download file 411 Bytes
-
https://huggingface.co/m4dma8/dinov3-convnext-balanced_finalrun/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://m4dma8/dinov3-convnext-balanced_finalrun/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/m4dma8/dinov3-convnext-balanced_finalrun/resolve/main/preprocessor_config.json
411 Bytes
| { | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "DINOv3ViTImageProcessorFast", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| } | |