GPt neo training dataset
@article{gao2020pile,
title={The Pile: An 800GB Dataset of Diverse Text for Language Modeling},
author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and others},
journal={arXiv preprint arXiv:2101.00027},
year={2020}
}