Models and training

Quantized low-rank adaptation (QLoRA)

stable definition

Definition

A fine-tuning method that trains LoRA adapters while keeping the base model frozen in a lower-precision quantized representation.

Distinguish it from nearby terms

LoRA reduces trainable parameters. QLoRA combines that approach with a quantized base model to reduce the memory required during fine-tuning.

Check your understanding

QLoRA makes adaptation more accessible on limited hardware, but it does not eliminate the need to evaluate quality changes from both training and quantization.