{"version":"1.0","type":"rich","provider_name":"gaks.ai AI Glossary","provider_url":"https://gaks.ai/glossary","title":"Supervised Fine-Tuning — AI Glossary","author_name":"Glenn Katrud Solheim","author_url":"https://gaks.ai","width":600,"height":200,"html":"

AI Glossary — gaks.ai

Supervised Fine-Tuning (SFT)

The initial stage of adapting a pre-trained language model to follow instructions, where the model is trained on a curated dataset of high-quality prompt-response pairs using standard supervised learning. SFT is typically the first step in turning a raw pre-trained model into a useful assistant, usually followed by preference optimization and reinforcement learning from human feedback.

Source: gaks.ai/glossary/supervised-fine-tuning →
"}