# Sirius Quantum

> Quantum data layer for Physical AI. Sirius Quantum Solutions publishes open, quantum-native machine-learning datasets on Hugging Face — exact FCI chemistry labels, quantum-kernel benchmarks, barren-plateau trajectories, portfolio-risk regimes — and builds ReLab, the quantum data relabelling engine that produces them.

Key facts:
- All public datasets are hosted at https://huggingface.co/SiriusQuantum and free to use.
- Datasets are quantum-relabeled or quantum-generated: labels come from exact quantum computation (FCI, quantum kernels, exact ground states), not classical approximations such as DFT.
- Loadable with the Hugging Face `datasets` library: `load_dataset("<slug>")`.
- ReLab engine early access: info@siriusquantum.com

## Datasets

- [SIRIUS-14k](https://huggingface.co/datasets/SiriusQuantum/sirius-14k): 13,800 labeled optimization trajectories across 4 VQA circuit architectures. The first public labeled dataset for barren plateau research, with gradient variance profiles, convergence diagnostics, and 24-field multi-label trainability annotations.
- [QM7b Quantum Relabeled](https://huggingface.co/datasets/SiriusQuantum/qm7b-quantum-relabeled): Quantum-relabeled subset of QM7b (7,211-molecule benchmark): 400 seven-heavy-atom molecules (300 train / 100 test) with a precomputed 7-qubit Heisenberg quantum-kernel matrix, quantum-native labels, and 1-RDM observables. Drop-in for scikit-learn precomputed-kernel pipelines, no quantum hardware required.
- [SQMolecular95k](https://huggingface.co/datasets/SiriusQuantum/SQMolecular95k): The 95k scale-up of SQMolecular: 94,376 geometries of exact FCI correlation energies, each paired in-file with its MP2 baseline. A harder cross-scaffold transfer benchmark that tests whether the quantum representation carries to unseen chemistry, not just unseen conformers.
- [BBBP Quantum Relabeled](https://huggingface.co/datasets/SiriusQuantum/bbbp-quantum-relabeled): Quantum-relabeled MoleculeNet BBBP benchmark for CNS drug penetration. 85 compounds encoded as a 25-qubit graph-Hamiltonian circuit, shipped as a precomputed pairwise quantum-fidelity kernel for drop-in SVM classification.
- [Quantum Finance Risk Benchmark](https://huggingface.co/datasets/SiriusQuantum/quantum-finance-risk-benchmark): 1,000 correlated-asset market regimes encoded as Ising-Hamiltonian quantum states with systemic portfolio-risk labels. Quantum features hold 0.69 test error at 16 assets where the classical kernel degrades to chance — a widening sample-efficiency gap.
- [SQMolecular](https://huggingface.co/datasets/SiriusQuantum/SQMolecular): 10,038 exact FCI correlation energies across 717 organic molecules, 14 thermal geometries each, paired in-file with matched MP2 baselines. A noise-free delta-learning target — every bit of model error is the model's, not the label's. Produced with the ReLab engine.
- [QM9 Quantum Relabeled](https://huggingface.co/datasets/SiriusQuantum/qm9-quantum-relabeled): Quantum-relabeled subset of QM9, the canonical 133,885-molecule small-molecule quantum-chemistry benchmark: 400 nine-heavy-atom molecules (300 train / 100 test) re-labeled with quantum-native targets alongside the original seventeen quantum-mechanical properties.
- [Quantum Ground States · 320 Qubits](https://huggingface.co/datasets/SiriusQuantum/quantum-ground-states-320-qubits): 750 exact ground states of disordered transverse-field Ising chains from 20 to 320 qubits, pairing local 1-RDM measurements with physical observables. A benchmark for learning properties of quantum states at a scale no state-vector simulator can reach.

## Platform

- [ReLab Engine](https://siriusquantum.com/): quantum data relabelling for AI stacks — replaces approximate classical labels with exact quantum-computed ones. Early access via info@siriusquantum.com.
- [Zilver](https://siriusquantum.com/zilver): a distributed quantum simulator, open source under Apache 2.0. Simulates larger circuits on integrated GPUs with unified memory, on Apple silicon and AMD. pip install zilver. Network nodes support Apple Mac mini, AMD Ryzen and NVIDIA.

## Optional

- [llms-full.txt](https://siriusquantum.com/llms-full.txt): full dataset documentation with schemas and load snippets
- [Hugging Face organization](https://huggingface.co/SiriusQuantum)
- [GitHub](https://github.com/Sirius-Quantum)
- [X / Twitter](https://x.com/SiriusQuantum)
- Contact: info@siriusquantum.com