thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

Parameter-Efficient Fine-Tuning (PEFT)

Fine-tuning methods that update only a small set of added or selected parameters while freezing the base model.

Definition

PEFT methods such as LoRA, QLoRA, adapters and prompt tuning cut memory and storage dramatically, allow many task adapters per base model, and reduce catastrophic forgetting.

Exam tip

PEFT is the default answer when fine-tuning must fit limited GPU memory or many tasks share one base model.

Related terms