AI Glossary Term

What is Parameter-Efficient Fine-Tuning (PEFT)?

Definition

Methods that adapt models by training a small subset of added parameters.

Related terms

Fine-Tuning
Continuing training on domain-specific data to adapt a pre-trained model to a specific task.
LoRA (Low-Rank Adaptation)
A parameter-efficient fine-tuning method that adds low-rank adapter matrices.
Post-training
Training steps applied after pretraining, such as instruction tuning, preference optimization, and safety tuning.
Instruction Tuning
Fine-tuning a model on instruction-response pairs to improve task following.
Learning Rate
A training hyperparameter controlling how much parameters change each update step.
DPO (Direct Preference Optimization)
A training method that fine-tunes models directly on preference pairs without needing a separate reward model.

Learn more in our free guides

Fine-TuningHard Parameter Sharing in Multi-Task NetworksGumbel-Softmax and ReparameterizationRejection Sampling Fine-Tuning
Browse the full AI GlossaryExplore all free AI guides