Weight quantization is a technique that reduces the number of bits used to represent weights. This is done by converting model weights from high-precision floating-point representations to low-precision floating-point or integer representations
Weight quantization
Creator
Creator
Seonglae ChoCreated
Created
2024 Jan 15 16:22Editor
Editor
Seonglae ChoEdited
Edited
2024 Jan 15 16:22Refs
Refs