Glossary term
Glossary term
Agentic Systems
A set of techniques to fine-tune a large pre-trained language model (PLM) more efficiently than full fine-tuning. Parameter-efficient tuning typically fine-tunes far fewer parameters than full fine-tuning, yet generally produces a large language model that performs as well (or almost as well) as a large language model built from full fine-tuning.
Compare and contrast parameter-efficient tuning with:
Parameter-efficient tuning is also known as parameter-efficient fine-tuning.
Created for this library
A SaaS team uses parameter-efficient tuning to adapt a foundation model to each enterprise customer without storing a full model per customer.
A legal-tech vendor uses parameter-efficient tuning to specialize a base LLM on contract data while keeping the base weights shared.
A research team uses parameter-efficient tuning to test many domain adaptations of a foundation model quickly.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License