Instructions to use tzhao3/vit-tiny-imagenet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tzhao3/vit-tiny-imagenet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="tzhao3/vit-tiny-imagenet") 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-tiny-imagenet") model = AutoModelForImageClassification.from_pretrained("tzhao3/vit-tiny-imagenet", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from tzhao3/vit-tiny-imagenet: direct link, hf CLI and curl.
- Browser
- Download file 344 MB
-
https://huggingface.co/tzhao3/vit-tiny-imagenet/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://tzhao3/vit-tiny-imagenet/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/tzhao3/vit-tiny-imagenet/resolve/main/pytorch_model.bin
344 MB
- Xet hash:
- c2beed8f0d4f1b0883917dab03eb29520362c8c5aa0d8ab7d469ea3fab78f100
- Size of remote file:
- 344 MB
- SHA256:
- 784de32ba049430b2536fd689516e9b9cf2b1d318af7ca0f0267b365acf2502f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.