Instructions to use Letian2003/unified_vit_v96_128-vision-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use Letian2003/unified_vit_v96_128-vision-decoder with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:Letian2003/unified_vit_v96_128-vision-decoder') tokenizer = open_clip.get_tokenizer('hf-hub:Letian2003/unified_vit_v96_128-vision-decoder') - Notebooks
- Google Colab
- Kaggle
Upload standalone vision decoder: v96 stage-1 PRE (res128, step 62556) reconstruction path
0445fbe verified - Xet hash:
- 04f521d7a99c613223b6316fbdb11932c8392bfb4576234999e24d0e7962469e
- Size of remote file:
- 154 MB
- SHA256:
- c316888b791e531c08f9626781f7dd20e0fc8485dffa98ef28cf8d405d0776f9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.