PEFT — Parameter-Efficient Fine-Tuning

Fact

A fine-tuning method that updates only a few model parameters.

In Plain Words

PEFT is like a clip-on basket for your old bike. The bike stays the same. Now it carries snacks.

Teams use it for private custom AI, with less memory and cost. But it still hits the base model’s limits.

Related Concepts

• Fine-tuning
• Low-Rank Adaptation
• Base model

Fine-tuning
PEFT is fine-tuning with fewer trainable parameters.

LoRA
LoRA is a common PEFT method for small low-rank changes.

Base model
PEFT usually freezes most of the base model and trains only small added parts.