Skip to content

Glossary: Fine-tuning LLMs

Fine-tuning

Also written: fine-tune, fine-tuned

Continuing to train a pretrained model on your own examples, so it keeps its general skills and picks up a new task or style. It changes the model's weights, unlike prompting or RAG.

Where the book teaches it

Related terms

Supervised fine-tuning (SFT)Full fine-tuningLoRA (low-rank adaptation)