News for hackers. Stuff that matters.
Re:DyLoRA: Parameter Efficient Tuning of Pre-Trained Models by huevosabio on Monday April 10, 2023 @04:35PM (#35517083)
Yea, this is interesting but I can't see the immidiate value (not that there isn't).

Maybe if the "optimal rank" of LORA applies to any adaptation and you interested in training multiple adaptations for different use cases?

There are no comments on this comment yet.