# Model Description:

This model is a T5-base model which is pre-trained on the C4 dataset and fine-tuned on the JFLEG dataset. T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.

The T5 model was presented in **Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer** by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu.

## Pre-Processing:
For this task of grammar correction, we’ll use the prefix “grammar: “ to each of the input sentences. This is done because T5 models are able to perform multiple tasks like translation and summarization with a single model, and a unique prefix is used for each task so that the model learns which task to perform.