Instructions to use HelloJiang/LAION-CLIP-ConvNeXt-Large-512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use HelloJiang/LAION-CLIP-ConvNeXt-Large-512 with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:HelloJiang/LAION-CLIP-ConvNeXt-Large-512') tokenizer = open_clip.get_tokenizer('hf-hub:HelloJiang/LAION-CLIP-ConvNeXt-Large-512') - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from HelloJiang/LAION-CLIP-ConvNeXt-Large-512: direct link, hf CLI and curl.
- Browser
- Download file 316 Bytes
-
https://huggingface.co/HelloJiang/LAION-CLIP-ConvNeXt-Large-512/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://HelloJiang/LAION-CLIP-ConvNeXt-Large-512/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/HelloJiang/LAION-CLIP-ConvNeXt-Large-512/resolve/main/preprocessor_config.json
316 Bytes
| { | |
| "crop_size": 512, | |
| "do_center_crop": true, | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "feature_extractor_type": "CLIPFeatureExtractor", | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "resample": 3, | |
| "size": 512 | |
| } | |