arXiv - CSCL: "LLMLingua: Compressing Prompts for Accelerated In…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models. (arXiv:2310.05736v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2310.05736 #arXiv #NLProc

Dec 07, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation