OK. It seems like we can use
layer[0].weight().int_repr().data
to get the INT8 representation of the weight entries.
Also,
layer[0].weight().dequantize()
gives the tensor of the weights in FP format to have element-wise access to its contents.
OK. It seems like we can use
layer[0].weight().int_repr().data
to get the INT8 representation of the weight entries.
Also,
layer[0].weight().dequantize()
gives the tensor of the weights in FP format to have element-wise access to its contents.