Closed WhenMelancholy closed 3 weeks ago
Should this line of code be changed to noise_v = self.v_noise.weight[0] + v ?
noise_v = self.v_noise.weight[0] + v
The noise is added into the query itself to make the noised self attention.
Should this line of code be changed to
noise_v = self.v_noise.weight[0] + v
?