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

Supervised Fine-Tuning (SFT)

Fine-tuning a model on labeled input-output pairs, such as instruction-response examples.

Definition

SFT is the first post-training stage that turns a base model into an instruction follower, and the most common way to customize models for tasks. Data quality and diversity matter more than volume.

Exam tip

SFT needs labeled prompt-response pairs; unlabeled domain text points to continued pretraining instead.

Related terms