@inproceedings{therefinedwebdatasetforfalconllm1,
  title = {The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only},
  year = {2023},
  booktitle = {NeurIPS 2023 11},
  url = {https://openreview.net/forum?id=kM5eGcdCzq},
}