Upload folder using huggingface_hub

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+tags:
+- pytorch
+- safetensors
+- threshold-logic
+- neuromorphic
+- voting
+---
+
+# threshold-5outof6
+
+At-least-5-of-6 threshold gate. Fires when 5 or more of the 6 inputs are high.
+
+## Function
+
+```
+5outof6(x0, x1, x2, x3, x4, x5) = 1 if (x0 + x1 + x2 + x3 + x4 + x5) >= 5
+```
+
+## Truth Table (selected)
+
+| Hamming Weight | Output |
+|:--------------:|:------:|
+| 0 | 0 |
+| 1 | 0 |
+| 2 | 0 |
+| 3 | 0 |
+| 4 | 0 |
+| 5 | 1 |
+| 6 | 1 |
+
+## Mechanism
+
+Single threshold neuron with uniform weights. The bias of -5 sets the firing threshold:
+
+- Sum = (number of 1s) + (-5)
+- Fires when sum >= 0, i.e., when Hamming weight >= 5
+
+## k-out-of-6 Family
+
+| Circuit | Bias | Fires when |
+|---------|------|------------|
+| 1-out-of-6 | -1 | HW >= 1 |
+| 2-out-of-6 | -2 | HW >= 2 |
+| 3-out-of-6 | -3 | HW >= 3 (majority) |
+| 4-out-of-6 | -4 | HW >= 4 |
+| 5-out-of-6 | -5 | HW >= 5 |
+| 6-out-of-6 | -6 | HW = 6 (AND) |
+
+## Parameters
+
+| | |
+|---|---|
+| Weights | [1, 1, 1, 1, 1, 1] |
+| Bias | -5 |
+| Inputs | 6 |
+| Outputs | 1 |
+| Neurons | 1 |
+| Layers | 1 |
+| Parameters | 7 |
+| Magnitude | 11 |
+
+## Usage
+
+```python
+from safetensors.torch import load_file
+import torch
+
+w = load_file('model.safetensors')
+
+def at_least_5_of_6(bits):
+    inputs = torch.tensor([float(b) for b in bits])
+    return int((inputs @ w['neuron.weight'].T + w['neuron.bias'] >= 0).item())
+
+print(at_least_5_of_6([1, 1, 1, 1, 1, 0, 0, 0]))  # 0 or 1 depending on k
+```
+
+## License
+
+MIT

config.json

@@ -0,0 +1,9 @@
+{
+  "name": "threshold-5outof6",
+  "description": "At-least-5-of-6 threshold gate",
+  "inputs": 6,
+  "outputs": 1,
+  "neurons": 1,
+  "layers": 1,
+  "parameters": 7
+}

create_safetensors.py

@@ -0,0 +1,26 @@
+import torch
+from safetensors.torch import save_file
+
+weights = {
+    'neuron.weight': torch.tensor([[1.0, 1.0, 1.0, 1.0, 1.0, 1.0]], dtype=torch.float32),
+    'neuron.bias': torch.tensor([-5.0], dtype=torch.float32)
+}
+save_file(weights, 'model.safetensors')
+
+def test(bits):
+    inputs = torch.tensor([float(b) for b in bits])
+    return int((inputs @ weights['neuron.weight'].T + weights['neuron.bias'] >= 0).item())
+
+print("Verifying 5-out-of-6...")
+errors = 0
+for i in range(64):
+    bits = [(i >> j) & 1 for j in range(6)]
+    result = test(bits)
+    expected = 1 if sum(bits) >= 5 else 0
+    if result != expected:
+        errors += 1
+if errors == 0:
+    print("All 64 test cases passed!")
+else:
+    print(f"FAILED: {errors} errors")
+print(f"Magnitude: {sum(t.abs().sum().item() for t in weights.values()):.0f}")

model.py

@@ -0,0 +1,20 @@
+import torch
+from safetensors.torch import load_file
+
+def load_model(path='model.safetensors'):
+    return load_file(path)
+
+def at_least_5_of_6(bits, weights):
+    """Returns 1 if at least 5 of 6 inputs are high."""
+    inputs = torch.tensor([float(b) for b in bits])
+    return int((inputs @ weights['neuron.weight'].T + weights['neuron.bias'] >= 0).item())
+
+if __name__ == '__main__':
+    w = load_model()
+    print('5-out-of-6 truth table by Hamming weight:')
+    for hw in range(7):
+        bits = [1 if i < hw else 0 for i in range(6)]
+        result = at_least_5_of_6(bits, w)
+        expected = 1 if hw >= 5 else 0
+        status = 'OK' if result == expected else 'FAIL'
+        print(f'  HW={hw}: {result} (expected {expected}) {status}')

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a7df3072cfc96fa32d074e7a8602f72d81199f19cc61dd72b473b9441b6f81
+size 172