← Glossary / 49 of 100
n. / Models and tokens
Fine-tuning
Definition
Fine-tuning is training an existing model a little further on your own examples so it follows a style, format or task more reliably. It changes the model itself, while prompting only changes its input.
In more detail
It is worth considering when you have many good examples and prompting alone is too long, costly or inconsistent. It is not a good way to add facts that change often; retrieval handles that better. Good traces and reviewed datasets are the raw material for a fine-tuning set, and an evaluation set tells you whether it helped.
Example
You collect 800 reviewed support replies in your brand voice, fine-tune a small model on them, and check it against a held-out set before replacing the large model.
