Glossary · Training & tuning

LoRA (low-rank adaptation)

A parameter-efficient fine-tuning method that trains small low-rank matrices injected into a frozen model instead of updating all its weights.

Related terms

• Hugging Face Transformers
• QLoRA
• alignment (LLM)
• direct preference optimization (DPO)
• extended thinking
• fine-tuning

Vynaris is an inference gateway that routes each request to the cheapest right-sized model and shows the receipt. Get an API key or read the docs.