What is PEFT (parameter-efficient fine-tuning)?

Question

Accepted Answer

Fine-tuning only a small subset of parameters instead of all of them — PEFT adapts a model by training a tiny fraction of its parameters — newly added adapter weights, or a small selected subset — which keeps optimizer state and memory low while matching full fine-tuning on many tasks. Shortening a full run, working layer by layer, or training on self-generated data all still update the whole model, so none of them is parameter-efficient.

Answer

Fine-tuning every weight, but for far fewer steps than a full run

Answer

Fine-tuning one layer at a time, to keep the optimizer state in memory

Answer

Fine-tuning on data the model generated itself, to avoid labelling cost

What is PEFT (parameter-efficient fine-tuning)?

Why this is the answer

More Customizing LLMs: Fine-tuning, LoRA & RAG flashcards