arXiv - CSCL: "Bi-Drop: Generalizable Fine-tuning for Pre-traine…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Bi-Drop: Generalizable Fine-tuning for Pre-trained Language Models via Adaptive Subnetwork Optimization. (arXiv:2305.14760v1 [cs.CL])

http://arxiv.org/abs/2305.14760 #arXiv #NLProc

May 25, 2023, 03:06 · · arxiv-cscl · · ·

Sign in to participate in the conversation