@misc{dey2023cerebras, title={Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster}, author={Nolan Dey and Gurpreet Gosal and Zhiming and Chen and Hemant Khachane and William Marshall and Ribhu Pathria and Marvin Tom and Joel Hestness}, year={2023}, eprint={2304.03208}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2304.03208} }