RWKV-LM-pile-dataset
pile dataset converted to binidx format for RWKV-LM using json2binidx_tool.
full upload: https://huggingface.co/datasets/RichardErkhov/RWKV-LM_pile_binidx_dataset
@article{pile,
title={The {P}ile: 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 Presser, Shawn and Leahy, Connor},
journal={arXiv preprint arXiv:2101.00027},
year={2020}
}
@software{peng_bo_2021_5196578,
author = {PENG Bo},
title = {BlinkDL/RWKV-LM: 0.01},
month = aug,
year = 2021,
publisher = {Zenodo},
version = {0.01},
doi = {10.5281/zenodo.5196577},
url = {https://doi.org/10.5281/zenodo.5196577}
}