bjergerk1ng

joined 1 year ago
sorted by: new top controversial old
[D] What is the motivation for parameter-efficient fine tuning if there's no significant reduction in runtime or GPU memory usage? in c/machinelearning@academy.garden
[–] bjergerk1ng@alien.top 1 points 11 months ago (1 children)

I think the big win comes from combining LoRA with quantization (i.e. QLoRA) which you can't normally do with full fine-tuning.