What is fine-tuning?
Fine-tuning is further training on your own examples, so the model behaves differently by default.
~/ai-glossary
$ glossary
1 of 4 in #models-and-tuning
It changes the model itself, which is why it costs real money and takes real data.
Almost nobody needs it. What people want from fine-tuning, sounding like them, they get from a voice file and good context, at zero cost.
Was this page helpful?