Applied AI·Fine-tuning and customisation

you hand it a few hundred prompt-and-ideal-answer pairs, which is what people mean by fine-tuning when they do not qualify it.

Supervised fine-tuning (SFT)

Also calledSFT

Draft summary, pending review

Fine-tuning on prompt-and-ideal-response pairs, the bread-and-butter phase for teaching format and behaviour. When someone says fine-tuning without qualification, they usually mean this.

Commonly confused with

Preference tuning (RLHF, DPO)

Preference tuning (RLHF, DPO) vs Supervised fine-tuning (SFT) →