Ep.6 — OPT: Open Pre-trained Transformer Language Models (Meta

Ep.6 — OPT: Open Pre-trained Transformer Language Models (Meta AI)

#Ep6 #OPT #Open #Pretrained #Transformer #Language #Models #Meta

“Zeta Alpha Vector”

Andrew Yates (Assistant Professor at the University of Amsterdam) and Sergi Castella i Sapé discuss the recent “Open Pre-trained Transformer (OPT) Language Models” from Meta AI (formerly Facebook). In this replication work, Meta developed and trained a 175 Billion parameter Transformer very…

source