This project is a structured replication of the Vision Transformer (ViT) architecture introduced by Google Research in the paper:
"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale"
Dosovitskiy et al., 2020 (arXiv:2010.11929)

• https://arxiv.org/pdf/2010.11929

The goal is to:

• Reproduce the model architecture and results on CIFAR-10 and TinyImageNet
• Validate core claims (e.g., performance vs CNNs)
• Extend the study with visualization and interpretability techniques

This is being developed as part of a personal research initiative to demonstrate competency in modern AI architectures.