arXiv - CSCL: "ZeroQuant(4+2): Redefining LLMs Quantization with…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks. (arXiv:2312.08583v1 [cs.CL])

http://arxiv.org/abs/2312.08583 #arXiv #NLProc

Dec 17, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation