# ViT-GPT2 Architecture

This is an image captioning model based on ViT and GPT2 architectures, capable of generating natural language descriptions for input images.

This is a vision-language model trained on the COCO dataset, capable of generating descriptive texts that include spatial relationships between image entities.

This is a spatially-aware vision-language model capable of recognizing spatial relationships between objects in images and generating descriptive text.

A ViT-GPT2 architecture captcha recognition model fine-tuned on a dataset of 60,000 images, capable of accurately identifying text in captcha images.

A vision-language model trained on the Flickr8k dataset, capable of generating natural language descriptions for input images