@article{therefinedwebdatasetforfalconllm, title = {The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only}, author = {Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay}, year = {2023}, eprint = {2306.01116}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.01116v1}, }