QLoRA

Also known as: Quantized LoRA

QLoRA combines 4-bit quantization of the frozen base model with LoRA adapter training, making it possible to fine-tune large language models on a single consumer GPU. The base model's weights are stored in NF4 format to minimize memory, while the trainable LoRA matrices are kept in higher precision. QLoRA has dramatically democratized fine-tuning by bringing it within reach of researchers and practitioners without access to large-scale GPU clusters.