arXiv - CSCL: "TCRA-LLM: Token Compression Retrieval Augmented L…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction. (arXiv:2310.15556v1 [cs.CL])

http://arxiv.org/abs/2310.15556 #arXiv #NLProc

Oct 25, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation