AI Vocabulary · 06 Own Your AI
What is Fine-Tuning?
Training an existing model further on your own examples to change its behaviour. Rarely the first step.
Fine-tuning takes a finished model and continues training it on a smaller set of your own examples, adjusting its parameters. It is useful for teaching a consistent style, format or specialised behaviour, for example classifying documents exactly the way your team does.
It is not the best way to give a model knowledge. Facts change, and retraining every time is slow and costly. For knowledge, RAG or simply good context usually works better and stays up to date.
Fine-tuning needs good example data, a way to measure results with evals, and a plan for maintaining the tuned model.
Why it matters for you
If someone proposes fine-tuning as step one, ask what better prompts and context already achieve. Fine-tune when you have hit the limits of those, and when you have hundreds of good examples.
Own it
Fine-tuning an open-weight model produces a model that is truly yours: your behaviour, on your infrastructure. That can be a real asset, if you can maintain it.
Where it comes from
Fine-tuning grew out of transfer learning, the idea of reusing what one model has learned for a new task. For language it took off in 2018, when Jeremy Howard of fast.ai and Sebastian Ruder showed in ULMFiT that a pretrained language model can be fine-tuned for new text tasks with little data. Pretrained large language models quickly made this the standard way to adapt AI.
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.