How to see the quantized weights?

quantization
1

like tensor.int_repr() can return the int values of quantized tensor, how can we get the int values of the quantized weights(_packed_params).
while printing the _packed_params, we can get a uint8 tensor, what does it stand for?

2

Yes. Please use <q_module>.weight(). It returns a quantized tensor of weights and you can use int_repr() to get the int8_t values of weights. Note: Weights are usually quantized with dtype = int8_t.