All guides
Models· 2 min

What is fine-tuning?

Fine-tuning adapts a pre-trained model to your data or task by continuing training on a smaller dataset.

Key idea

Take a general model, show it examples of the behavior you want, and update its weights so it becomes a specialist.

Example

Fine-tune a base Llama model on your company's support tickets to sound on-brand and know your product.

What to remember

  • Full fine-tuning updates all weights — expensive
  • LoRA / QLoRA train tiny adapters — cheap and swappable
  • Often unnecessary — try RAG or prompting first