# LoRA

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: low-rank adaptation, low rank adaptation, LoRAs, QLoRA, adapter, adapters

Low-rank adaptation. A cheap way to [fine-tune](https://ecosystem.samcarlton.com/fine-tuning) a model by training a small add-on set of [weights](https://ecosystem.samcarlton.com/weights) instead of changing the whole model. The add-on file is small and can be swapped in and out.

**For example:** A company trains a LoRA on its brand voice in a few hours on one [GPU](https://ecosystem.samcarlton.com/gpu) and loads it on top of an [open-weights model](https://ecosystem.samcarlton.com/open-source-vs-open-weights).

## Connects to (4)

- [Fine-tuning](https://ecosystem.samcarlton.com/fine-tuning): Extra training of an existing model on a smaller, narrower set of examples, so it suits one task or style.
- [Weights](https://ecosystem.samcarlton.com/weights): The numbers inside a model that it learned during training.
- [Open source vs open weights](https://ecosystem.samcarlton.com/open-source-vs-open-weights): Two labels for AI models that people often mix up.
- [Quantization](https://ecosystem.samcarlton.com/quantization): Shrinking a model by storing its weights with fewer digits of precision.

Map view: https://ecosystem.samcarlton.com/lora