Downloads · 30 days
0
quantum-mnist-1000qubit
Reality123b/quantum-mnist-1000qubit
quantum-mnist-1000qubit is a machine learning model from Reality123b. 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.
Pure quantum ML model — trained entirely on QPU-1 with zero classical neural network.
Access
Public
Updated Apr 27, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 52%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026
- SHA
- c1f88f11
Datasets
Model card
From the Hugging Face model README
🔮 1000-Qubit Quantum MNIST Classifier
Pure quantum ML model — trained entirely on QPU-1 with zero classical neural network.
Architecture
| Component | Qubits | Details |
|---|---|---|
| Input | 0-783 | Ry angle encoding (28×28 pixels) |
| Variational | 784-989 | 206 qubits, 2 layers (Ry + CNOT) |
| Output | 990-999 | 10 qubits (one per digit class) |
| Total | 1000 |
- 422 trainable parameters (Ry rotation angles)
- Training method: Parameter-shift rule (fully quantum gradients)
- Compute: QPU-1 by Lap Quantum
How it works
- Encoding: Each MNIST pixel is encoded as a Ry rotation on input qubits
- Variational layers: Parameterized Ry gates + CNOT entanglement ladders
- Cross-entanglement: Input qubits connected to variational qubits
- Readout: 10 output qubits measured; argmax = predicted digit
- Gradients: Parameter-shift rule — shift each angle by ±π/2, measure loss difference
Train it yourself
Use the trainer Space: Reality123b/quantum-mnist-1000qubit-trainer
Awaiting first training run — click "Train on QPU-1" in the Space to generate weights.
- License
- mit
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026