arXiv - CSCL: "Towards A Unified View of Sparse Feed-Forward Net…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model. (arXiv:2305.13999v3 [cs.CL] UPDATED)

http://arxiv.org/abs/2305.13999 #arXiv #NLProc

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

Sign in to participate in the conversation