SFT (supervised fine-tuning) is training on "request → desired answer" pairs.

In depth: 10 · Fine-tuning: when and how → “SFT: learning from examples”

Related: LoRA · model

Appears in

• 10 · Model Training: Practice: fine-tune a small model

The course is free — start on the site →

Write to the author: Telegram · LinkedIn

checked against the course: 2026-11-02 · 664b147