Dheiver Francisco Santos

Parameter-Efficient Fine-Tuning: LoRA, QLoRA, and DoRA

2026 · Zenodo (CERN European Organization for Nuclear Research)

A technical note comparing parameter-efficient fine-tuning techniques for large language models, including Low-Rank Adaptation (LoRA), its quantized variant QLoRA, and Weight-Decomposed Low-Rank Adaptation (DoRA).