| import torch |
| from safetensors.torch import load_file |
|
|
| def load_model(path='model.safetensors'): |
| return load_file(path) |
|
|
| def xor2(a, b, prefix, w): |
| or_out = int(a * w[f'{prefix}.or.weight'][0] + b * w[f'{prefix}.or.weight'][1] + w[f'{prefix}.or.bias'] >= 0) |
| nand_out = int(a * w[f'{prefix}.nand.weight'][0] + b * w[f'{prefix}.nand.weight'][1] + w[f'{prefix}.nand.bias'] >= 0) |
| return int(or_out * w[f'{prefix}.and.weight'][0] + nand_out * w[f'{prefix}.and.weight'][1] + w[f'{prefix}.and.bias'] >= 0) |
|
|
| def parity5(a, b, c, d, e, weights): |
| xor_ab = xor2(a, b, 'xor_ab', weights) |
| xor_cd = xor2(c, d, 'xor_cd', weights) |
| xor_abcd = xor2(xor_ab, xor_cd, 'xor_abcd', weights) |
| return xor2(xor_abcd, e, 'xor_final', weights) |
|
|
| if __name__ == '__main__': |
| w = load_model() |
| print('parity5 selected outputs:') |
| for n_ones in range(6): |
| bits = [1 if j < n_ones else 0 for j in range(5)] |
| print(f' {n_ones} ones: {bits} -> {parity5(*bits, w)}') |
|
|
