arXiv - CSCL: "ResidualTransformer: Residual Low-rank Learning w…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

ResidualTransformer: Residual Low-rank Learning with Weight-sharing for Transformer Layers. (arXiv:2310.02489v1 [cs.CL])

http://arxiv.org/abs/2310.02489 #arXiv #NLProc

Oct 05, 2023, 03:17 · · arxiv-cscl · · ·

Sign in to participate in the conversation