threshold-mod10

Trivial case: computes Hamming weight mod 10 for 8-bit inputs. Since max HW is 8 < 10, this is just HW.

Circuit

  x₀ x₁ x₂ x₃ x₄ x₅ x₆ x₇
   │  │  │  │  │  │  │  │
   │  │  │  │  │  │  │  │
   w: 1  1  1  1  1  1  1  1
   └──┴──┴──┴──┼──┴──┴──┴──┘
               ▼
          ┌─────────┐
          │ b:  0   │
          └─────────┘
               │
               ▼
       HW (= HW mod 10)

Why Trivial?

For mod m where m > (number of inputs), no reset ever occurs:

• 8 inputs → max HW = 8
• 8 mod 10 = 8 (no wraparound)

Parameters

Weights	[1, 1, 1, 1, 1, 1, 1, 1]
Bias	0
Total	9 parameters

Usage

from safetensors.torch import load_file
import torch

w = load_file('model.safetensors')

def mod10(bits):  # Actually just HW
    inputs = torch.tensor([float(b) for b in bits])
    return int((inputs * w['weight']).sum() + w['bias'])

Files

threshold-mod10/
├── model.safetensors
├── model.py
├── config.json
└── README.md

License

MIT