AI glossary · Generative AI and LLMs
Distillation
Distillation trains a smaller AI model to copy the behaviour of a larger one, so you get much of the quality at a fraction of the size and cost.
Also called knowledge distillation, model distillation
In more detail
The large “teacher” model answers many examples, and the small “student” model learns to give similar answers. The student is faster and cheaper, which makes it suitable for phones or high-volume apps.
Many small language models and “mini” versions of popular models are made this way.
Related terms
Small language model (SLM)A small language model (SLM) is a compact language model with far fewer parameters than an LLM, built to be fast, cheap and able to run on a phone or laptop.QuantizationQuantization shrinks an AI model by storing its numbers with less precision, so it uses less memory and runs faster, with a small loss in quality.Local AILocal AI means running an AI model on your own phone or computer instead of on a company’s servers, so it can work offline and keep your data on your device.
Browse related tools
AI tools listed on BroUseAI in these categories.
