@misc{ma2024llms, title={The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits}, author={Shuming Ma and Hongyu Wang and Lingxiao Ma and Lei Wang and Wenhui Wang and Shaohan Huang and Li Dong and Ruiping Wang and Jilong Xue and Furu Wei}, year={2024}, eprint={2402.17764}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2402.17764} }