%0 Generic %1 ma2024era %A Ma, Shuming %A Wang, Hongyu %A Ma, Lingxiao %A Wang, Lei %A Wang, Wenhui %A Huang, Shaohan %A Dong, Li %A Wang, Ruiping %A Xue, Jilong %A Wei, Furu %D 2024 %K llm nlp reading smol %T The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

@misc{ma2024era, added-at = {2024-04-19T09:31:46.000+0200}, archiveprefix = {arXiv}, author = {Ma, Shuming and Wang, Hongyu and Ma, Lingxiao and Wang, Lei and Wang, Wenhui and Huang, Shaohan and Dong, Li and Wang, Ruiping and Xue, Jilong and Wei, Furu}, biburl = {https://www.bibsonomy.org/bibtex/2c37de034d5b854f1a6ae851f49728763/tobias.koopmann}, description = {The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits}, eprint = {2402.17764}, interhash = {afcad28d08063d1c50a06d7fc8cc1aca}, intrahash = {c37de034d5b854f1a6ae851f49728763}, keywords = {llm nlp reading smol}, primaryclass = {cs.CL}, timestamp = {2024-04-19T09:31:46.000+0200}, title = {The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits}, year = 2024 }