Knowledge Graph — Coursera Notes › Academic disciplines › Information Technology / Computer Science › Artificial Intelligence › Deep Learning › Model Training › Fine-tuning

QLoRA

concept · part of Fine-tuning

Quantized Low-Rank Adaptation (QLoRA) is a fine-tuning technique that combines quantization and low-rank adaptation to reduce memory and computational requirements while maintaining model performance. It quantizes model weights to lower precision (e.g., 8-bit or 4-bit) and applies LoRA to specific layers, enabling fine-tuning of large models on smaller hardware like consumer GPUs.

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.