Google didn't publish vit-tiny and vit-small model checkpoints in HF中国镜像站. I converted the weights from the timm repository. This model is used in the same way as ViT-base.

Note that [safetensors] model requires torch 2.0 environment.

Downloads last month
4,823,694
Safetensors
Model size
5.72M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for WinKawaks/vit-tiny-patch16-224

Finetunes
32 models
Quantizations
1 model

Space using WinKawaks/vit-tiny-patch16-224 1