PyContinual icon indicating copy to clipboard operation
PyContinual copied to clipboard

Published 20 hours ago • verified publisher icon ZixuanKe

About Weight

Open Hephaestusxg opened this issue 7 months ago • 0 comments

Sry, excuse me.I would like to inquire about how to save model weights. In the newsgroup training, is it necessary to train 10 categories first and then proceed with incremental training? Or do you add ten categories to the existing BERT based on datasets_random?

Hephaestusxg avatar Jul 07 '24 09:07 Hephaestusxg