arXiv - CSCL: "SOLAR 10.7B: Scaling Large Language Models with S…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling. (arXiv:2312.15166v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2312.15166 #arXiv #NLProc

Jan 01, 2024, 03:20 · · arxiv-cscl · · ·

Sign in to participate in the conversation