Supervised Fine-Tuning

Adapting a pretrained model using curated input-and-output examples.

Supervised fine-tuning continues training a pretrained model on examples containing an instruction and a preferred response. The process teaches the model how to follow directions or perform specialised tasks.

SFT is commonly used after general pretraining and before preference optimisation. Its effectiveness depends heavily on the quality, diversity and consistency of the training examples.

Also in

Diffusion Models Small Language Models Retrieval-Augmented Generation Prompt Engineering Context Engineering Few-Shot Learning

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace