Instructions to use tzhao3/vit-CIFAR10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tzhao3/vit-CIFAR10 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="tzhao3/vit-CIFAR10") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("tzhao3/vit-CIFAR10") model = AutoModelForImageClassification.from_pretrained("tzhao3/vit-CIFAR10", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from tzhao3/vit-CIFAR10: direct link, hf CLI and curl.
- Browser
- Download file 687 MB
-
https://huggingface.co/tzhao3/vit-CIFAR10/resolve/main/optimizer.pt
- Command line
-
hf download hf://tzhao3/vit-CIFAR10/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/tzhao3/vit-CIFAR10/resolve/main/optimizer.pt
687 MB
- Xet hash:
- 4aba63d131135f5a2084f35f8aa4a0c936d68b60fdd41634b6955ceb008fc087
- Size of remote file:
- 687 MB
- SHA256:
- a5646207b658f1abcde060b92d6a0cf64cbd212157293dbea6207fb128d4be08
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.