Glossary · Definition
Fine-tuning
Fine-tuning is further training of an existing model on your own input–output examples to make its behaviour — format, style, classification — more consistent.
By Nythrex EngineeringUpdated 1 min read
In plain words
A base model already knows language. Fine-tuning shows it hundreds or thousands of examples of exactly how you want a specific task done, so it does that task more consistently or a smaller model can match a larger one on it. It’s good for behaviour, weak for teaching facts.
When it matters to you
- A narrow task at high volume
- Strict output format or house style that prompting can’t hold
- You have many reviewed examples
Common pitfalls
- Fine-tuning to add knowledge (RAG is usually better)
- No baseline comparison with a well-prompted model
- Too few or unreviewed examples
Keep reading
GuideRAG vs fine-tuning vs promptingRAG adds knowledge, fine-tuning changes behaviour, prompting is where you start. How to choose — with a decision tree, costs and pitfalls.Free toolRAG vs fine-tuning decision toolUp to four yes/no questions → a recommendation: RAG, fine-tuning, long-context prompting or better prompts, plus the next step to validate it.GlossaryPrompt engineeringPrompt engineering is designing the instructions, examples and context given to a language model so it performs a task reliably.
Want a second opinion on your project?
Tell us what you’re building and where you’re stuck. We’ll reply within one business day with the most practical next step — even if that step isn’t us.