from math import exp hidden = [1.0, 2.0, 3.0] sublayer = [0.2, -0.3, 0.1] residual = [x+y for x, y in zip(hidden, sublayer)] logits = [2.0, 1.0, 0.0] shifted = [exp(x-max(logits)) for x in logits] probabilities = [x/sum(shifted) for x in shifted] print("Residual:", [round(x, 1) for x in residual]) print("Probabilities:", [round(x, 3) for x in probabilities])