Weight quantization

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 Jan 15 16:22
Editor
Edited
Edited
2024 Jan 15 16:22
Refs
Refs
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
 
 
 
 
 
 
 
 

Recommendations