---
license: apache-2.0
---

# Vision Transformer

Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224. It was introduced in the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929).
The weights were converted from the `ViT-L_16.npz` file in [GCS buckets](https://console.cloud.google.com/storage/browser/vit_models/imagenet21k/) presented in the [original repository](https://github.com/google-research/vision_transformer).