Parameter-Efficient Fine-Tuning (PEFT)
Parameter-efficient fine-tuning is a set of methods that adapt a large model by training only a small number of extra or selected parameters rather than all of them.
What is Parameter-Efficient Fine-Tuning (PEFT)?
PEFT makes customising very large models affordable and lets many task-specific adapters share one base model. LoRA is the most popular method.
How it works
The original weights are frozen and small trainable components are added or a few layers are unfrozen.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions