# Distilled Vision Transformer

An image classification model fine-tuned on the mriDataSet dataset based on facebook/deit-base-distilled-patch16-224, achieving an accuracy of 99.01%

The distilled version of the Efficient Data Image Transformer (DeiT) model was pre-trained and fine-tuned on ImageNet-1k at 224x224 resolution, extracting knowledge from a teacher model through distillation learning.