jargon

Applied AI·Fine-tuning and customisation

you train a small fraction of the parameters and the memory bill drops by orders of magnitude.

Parameter-efficient fine-tuning (PEFT)

Also calledPEFT

Draft summary, pending review

The family of methods that adapt a model while training only a small fraction of parameters, cutting memory and cost by orders of magnitude. LoRA is the member you will actually meet.

Commonly confused with