Downloads · 30 days
15
36% of all-time downloads
threshold-minority7
phanerozoic/threshold-minority7
threshold-minority7 is a machine learning model from phanerozoic. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
7-input minority gate. Outputs 1 when at most 3 of 7 inputs are high. Complement of majority7.
All-time downloads
42
Public
Parameters
8
Likes
0
Public
Repo makeup
Click a slice to open those files.
.py1.4 KB · 53%
At a glance
- License
- mit
- Access
- Public
- Created
- Jan 23, 2026
- Updated
- Jan 23, 2026
- SHA
- a3a50d26
Model card
From the Hugging Face model README
threshold-minority7
7-input minority gate. Outputs 1 when at most 3 of 7 inputs are high. Complement of majority7.
Function
minority7(a, b, c, d, e, f, g) = 1 if sum <= 3, else 0
Architecture
Single neuron: weights [-1, -1, -1, -1, -1, -1, -1], bias 3
Fires when: sum <= 3
Parameters
| Inputs | 7 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 8 |
| Magnitude | 10 |
Usage
from safetensors.torch import load_file
import torch
w = load_file('model.safetensors')
def minority7(a, b, c, d, e, f, g):
inp = torch.tensor([float(a), float(b), float(c), float(d), float(e), float(f), float(g)])
return int((inp @ w['neuron.weight'].T + w['neuron.bias'] >= 0).item())
print(minority7(0, 0, 0, 0, 1, 1, 1)) # 1
print(minority7(0, 0, 0, 1, 1, 1, 1)) # 0
License
MIT
- License
- mit
- Created
- Jan 23, 2026
- Updated
- Jan 23, 2026