Upload 9 files

X_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f86f0040e6db07589dbb41db72f387f3e0fe8af5b7ef51373085ac8e56d68e1
+size 192

X_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97e1c30a771fa45d3b39f84afbb0d64861051fb53f0db0bca7037984b5dc883
+size 256

config.json

@@ -0,0 +1,21 @@
+{
+  "model_type": "quantum_neural_network",
+  "architecture": "hardware_efficient_ansatz",
+  "num_qubits": 2,
+  "num_parameters": 6,
+  "trainable_parameters": 4,
+  "circuit_depth": 4,
+  "backend": "ibm_fez",
+  "task": "binary_classification",
+  "dataset": "two_moons",
+  "train_samples": 8,
+  "test_samples": 4,
+  "qiskit_version": "1.0.0",
+  "framework": "qiskit",
+  "license": "apache-2.0",
+  "creation_date": "2025-12-06",
+  "gates": {
+    "ry": 6,
+    "cx": 1
+  }
+}

qnn_inference.py

@@ -0,0 +1,117 @@
+
+from qiskit import qpy
+from qiskit.circuit import ParameterVector
+from qiskit_machine_learning.neural_networks import SamplerQNN
+from qiskit_machine_learning.algorithms.classifiers import NeuralNetworkClassifier
+from qiskit.primitives import Sampler
+import numpy as np
+from huggingface_hub import hf_hub_download
+
+
+def load_qnn_model(repo_id="squ11z1/Two-Moons"):
+ 
+    # Download files
+    circuit_path = hf_hub_download(repo_id=repo_id, filename="circuit.qpy")
+    weights_path = hf_hub_download(repo_id=repo_id, filename="weights.npy")
+    
+    # Load circuit
+    with open(circuit_path, 'rb') as f:
+        circuit = qpy.load(f)[0]
+    
+    # Load weights
+    weights = np.load(weights_path)
+    
+    return circuit, weights
+
+
+def create_qnn_classifier(circuit, weights):
+
+    # Get parameters from circuit
+    input_params = [p for p in circuit.parameters if p.name.startswith('x')]
+    weight_params = [p for p in circuit.parameters if p.name.startswith('w')]
+
+    # Parity interpretation function
+    def parity(x):
+        # Convert to binary string and count ones
+        return bin(x).count("1") % 2
+
+    # Create sampler (using V2 to avoid deprecation)
+    from qiskit.primitives import StatevectorSampler as Sampler
+
+    sampler = Sampler()
+
+    # Create QNN
+    qnn = SamplerQNN(
+        circuit=circuit,
+        input_params=input_params,
+        weight_params=weight_params,
+        interpret=parity,
+        output_shape=2,
+        sampler=sampler
+    )
+    
+    # Create classifier
+    classifier = NeuralNetworkClassifier(
+        neural_network=qnn,
+        optimizer=None  # Pre-trained
+    )
+    
+    # Set weights
+    classifier._fit_result = type('obj', (object,), {'x': weights})
+    
+    return classifier
+
+
+def predict(X, repo_id="squ11z1/Two-Moons"):
+   
+    # Load model
+    circuit, weights = load_qnn_model(repo_id)
+    
+    # Create classifier
+    classifier = create_qnn_classifier(circuit, weights)
+    
+    # Predict
+    predictions = classifier.predict(X)
+    
+    return predictions
+
+
+# Example usage
+if __name__ == "__main__":
+    print("="*70)
+    print("Quantum Neural Network - Inference Example")
+    print("="*70)
+    
+    # Example: Load and predict
+    repo_id = "squ11z1/Two-Moons"
+    
+    print("\n1. Loading model from Hugging Face...")
+    circuit, weights = load_qnn_model(repo_id)
+    print(f"Circuit: {circuit.num_qubits} qubits, depth {circuit.depth()}")
+    print(f"Weights: {weights}")
+    
+    print("\n2. Creating classifier...")
+    classifier = create_qnn_classifier(circuit, weights)
+    print(f" Classifier ready")
+    
+    print("\n3. Making predictions...")
+    # Example data (Two Moons-like points)
+    X_test = np.array([
+        [0.5, 0.2],   # Class 1
+        [-0.5, 0.5],  # Class 0
+        [1.0, 0.0],   # Class 1
+        [-1.0, 0.8]   # Class 0
+    ])
+    
+    predictions = classifier.predict(X_test)
+    
+    print(f"\n   Input data:")
+    for i, x in enumerate(X_test):
+        print(f"     Sample {i+1}: {x}")
+    
+    print(f"\n   Predictions: {predictions}")
+    print(f"     (0 = Negative class, 1 = Positive class)")
+    
+    print("\n" + "="*70)
+    print("Inference complete!")
+    print("="*70)

requirements.txt

@@ -0,0 +1,8 @@
+qiskit>=1.0.0
+qiskit-aer>=0.13.0
+qiskit-machine-learning>=0.7.0
+qiskit-algorithms>=0.3.0
+numpy>=1.24.0
+scikit-learn>=1.3.0
+matplotlib>=3.7.0
+huggingface-hub>=0.20.0

weights.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b86c9f8617fbe53406f0e4699496a4e84fb32882fe283abc5c4e73770a1eb04
+size 160

y_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fbb199e82fb38f1f2d14b378fb2c24423b540848437f63b8572eea4c23c0e3
+size 160

y_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63422c1230165e6e7b67b1b0f3722075662908438eb34a1be9e25f6c9e975e6f
+size 192