News for hackers. Stuff that matters.
Re:Can LLMs learn from a single example? by jacquesm on Wednesday September 06, 2023 @05:04AM (#37402810)
You could simulate this by selectively locking and unlocking 'banks' of weights from a larger model to keep the influence there during training and to avoid losing them. Sort of a selective write-protect.

There are no comments on this comment yet.