Model Description:
To create t5-base-c4jfleg model, T5-base model is fine-tuned on the JFLEG dataset and C4 200M dataset by taking around 3000 examples from each with the objective of grammar correction.
The original Google's [T5-base] model was pre-trained on C4 dataset.
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.
Usage :
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("team-writing-assistant/t5-base-c4jfleg")
model = AutoModelForSeq2SeqLM.from_pretrained("team-writing-assistant/t5-base-c4jfleg")
Examples :
Input: My grammar are bad.
Output: My grammar is bad.
Input: Speed of light is fastest than speed of sound
Output: Speed of light is faster than speed of sound.