MWA4(The bit width of the weights is mixed, the bit width of the activation is 4) quantization problem of resnet18
maibaodexiaohangjiaya opened this issue · comments
maibaodexiaohangjiaya commented
I used the model (resnet18) provided by the project and the default parameters of the code to run MWA4 quantization. The results are quite different from those in the paper. Are there any other specific settings required to activate quantization to 4 bits?