Skip to content
AImpact
IT EN
Training Intermediate Also known as: Low-Rank Adaptation

LoRA

/lor-ah/

A fine-tuning technique that trains only a small set of extra parameters instead of the whole model, cutting compute cost and the size of the resulting file.

ShareLinkedInX

In practice

It lets you customize a 70-billion-parameter model on a consumer GPU. You save adapters of a few MB that plug on top of the base model. It is the practical standard for adapting open-weight models to specific use cases.

Related terms

Fine-tuning Quantization

Seen in the wild

3 entries mentioning it
  1. AI supply chain attacks: poisoned models, malicious LoRA adapters, and backdoored GGUF files
    High
  2. bitsandbytes 0.43: QLoRA and NF4/FP4 quantization for 4-bit fine-tuning
    Medium
  3. S-LoRA and Punica: serving hundreds of LoRA fine-tunings from a single base model
    High
← All terms