MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation.
Simiao Zuo, Qingru Zhang, Chen Liang, Pengcheng He, Tuo Zhao, Weizhu Chen
Browse the full NAACL paper archive.
Simiao Zuo, Qingru Zhang, Chen Liang, Pengcheng He, Tuo Zhao, Weizhu Chen
Browse the full NAACL paper archive.