# Fine-Tuning

> Fine-tuning continues training a pretrained model on your own examples, changing its weights to teach durable behavior, format, or domain style.

**Fine-tuning is continuing a pretrained model's training on your own dataset, updating its weights so desired behavior becomes part of the model itself rather than something you re-explain in every prompt.**

A base model knows language and the world; fine-tuning specializes it — your output format, your tone, your domain's conventions, a narrow task done exactly your way. The modern default is parameter-efficient tuning ([LoRA/QLoRA](/glossary/lora)), which trains small adapter matrices instead of all weights, putting real fine-tunes within reach of a single GPU.

The decision that matters comes before any training: **is your problem behavior or knowledge?** Behavior gaps fine-tune well; knowledge gaps belong in [RAG](/glossary/rag), and one-off instructions belong in the prompt. That decision tree — including when [distillation](/glossary/distillation) beats both — is mapped in [Fine-Tune vs RAG vs Prompt vs Distill](/guides/mlops/finetune-vs-rag-vs-prompt). And the unglamorous truth of the craft: the dataset is the model. Curation, cleaning, and eval splits ([the playbook](/guides/mlops/finetune-dataset-prep)) determine more of the outcome than any hyperparameter.

---

_Source: https://agentscamp.com/glossary/fine-tuning — Term on AgentsCamp._