arXiv - CSCL: "Scaling Pre-trained Language Models to Deeper via…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture. (arXiv:2303.16753v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2303.16753 #arXiv #NLProc

Apr 12, 2023, 03:06 · · arxiv-cscl · · ·

Sign in to participate in the conversation