AI Glossary
PEFT (Parameter-Efficient Fine-Tuning)
What is PEFT (Parameter-Efficient Fine-Tuning)?
A family of techniques that fine-tune a small subset of a model's parameters (or add small adapter layers) rather than updating all weights. PEFT methods like LoRA and Prefix Tuning dramatically reduce the compute cost of fine-tuning large models. They have made domain-specific model adaptation practical for organisations without large GPU clusters.
Example in practice
A mid-sized company that wants to specialise a model on their industry terminology but cannot afford full fine-tuning would use PEFT via LoRA — adapting only a small fraction of the model's weights at a fraction of the compute cost.
Learn more
See PEFT (Parameter-Efficient Fine-Tuning) applied in a professional context through this free course.
AI Strategy for Leaders →