Skip to main content
All terms
Training

Fine-Tuning

Further training a pretrained model on your own data to specialize it.

Definition

Fine-tuning continues training a pretrained model on a smaller, task- or subject-specific dataset so it adapts its behavior, style, or knowledge. Full fine-tuning updates all of the model's internal values and is expensive; lighter methods like LoRA update only a small number of added values, making it far cheaper.