Index Ai Academy
Glossary · Phase 6 · Modern LLM engineering

Parameter-efficient fine-tuning

Also written: PEFT

Fine-tuning that trains only a small number of new or chosen weights, such as LoRA adapters, instead of the whole model.

Learn it properly

Prompting vs RAG vs fine-tuning · Pick the cheapest approach that works. About 30 minutes.

Open the lesson Create a free account

Other terms from the same lesson