News for hackers. Stuff that matters.
Re:Pathways Language Model (PaLM): Scaling to 540B parameters by aceon48 on Monday April 04, 2022 @09:58PM (#30914451)
Would that even work? Using the pretrained model, wouldn’t you then be in the “local” optimum?

Although from a transfer learning perspective, chopping off last layers and retraining… You are prob right

There are no comments on this comment yet.