Hi! I noticed that in your code, you set bits_weights=8 and bits_activations=32 for first layer as default, it's not what is claimed in your paper " For the first and last layers of all quantized models, we quantize both weights and activations to 8-bit. " And I see an accuracy drop if I adjust the bits_activations to 8 for the first layer, could u please explain what is the reason? Thanks!
Hi! I noticed that in your code, you set
bits_weights=8
andbits_activations=32
for first layer as default, it's not what is claimed in your paper " For the first and last layers of all quantized models, we quantize both weights and activations to 8-bit. " And I see an accuracy drop if I adjust thebits_activations
to 8 for the first layer, could u please explain what is the reason? Thanks!