Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Hamza Alobeidli, Alessandro Cappelli, Baptiste Pannier, Ebtesam Almazrouei, Julien Launay. The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]
@inproceedings{PenedoMHCACPAL23, title = {The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only}, author = {Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Hamza Alobeidli and Alessandro Cappelli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay}, year = {2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/fa3ed726cc5073b9c31e3e49a807789c-Abstract-Datasets_and_Benchmarks.html}, researchr = {https://researchr.org/publication/PenedoMHCACPAL23}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, }