QLoRA
Definition
Quantized Low-Rank Adaptation. Running LoRA adapters on top of a base model quantized to 4-bit precision to save GPU memory.
Example Case
Fine-tuning a 13B model on a single 24GB VRAM GPU.
Quantized Low-Rank Adaptation. Running LoRA adapters on top of a base model quantized to 4-bit precision to save GPU memory.