Skip to content

Glossary: Fine-tuning LLMs

PEFT (parameter-efficient fine-tuning)

Also written: PEFT, peft

Methods that train only a small number of extra parameters, and the Hugging Face library that implements them. It provides `LoraConfig` and `get_peft_model`.

Where the book teaches it

Related terms

LoRA (low-rank adaptation)AdapterTRL