@article{15pintstechnicalreportpretrainingin, title = {1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data}, author = {Calvin Tan and Jerome Wang}, year = {2024}, eprint = {2408.03506}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.03506v1}, }