Quantization of Models

say it: “kwon-tih-ZAY-shun uv MOD-ulz” /ˌkwɑntəˈzeɪʃən əv ˈmɑdəlz/

Shrinking a model by storing weights with fewer bits.

What is Quantization of Models?

Quantization stores a model's weights with fewer bits, making it smaller and faster to run with a little quality loss.

Level: Master · More AI Basics terms at this level

Updated