mirror of
https://github.com/NousResearch/atropos.git
synced 2026-04-19 12:57:58 +00:00
Complete quantum-hybrid environment submission
- README.md: Updated documentation with WandB links and metrics - requirements.txt: Updated Python dependencies - atropos.py: Main environment implementation - atopos_quant.py: Additional quantum environment module - quantum_hybrid_artifacts.tar.gz: Compressed training artifacts
This commit is contained in:
jeannemtl
parent
39415d299e
commit
c4a972d433
3 changed files with 688 additions and 18 deletions
|
|
@ -1,58 +1,57 @@
|
|||
Quantum-Classical Hybrid Language Model Environment
|
||||
A novel Atropos environment that trains quantum-enhanced language models by combining classical transformers with quantum circuits using PennyLane and PyTorch.
|
||||
|
||||
Overview
|
||||
This environment implements a quantum-classical hybrid architecture for next-word prediction, trained on high-quality text generated by Hermes-3-70B. The key innovation is using quantum circuits to enhance traditional neural networks for language modeling tasks.
|
||||
|
||||
Research Question
|
||||
Can quantum circuits provide advantages over purely classical approaches in natural language processing tasks?
|
||||
|
||||
Architecture
|
||||
Data Flow
|
||||
Input Prompts → Hermes-3-70B (text generation) → Hybrid Model Training → Quantum-Enhanced Predictions
|
||||
Hybrid Model Components
|
||||
|
||||
Classical Pathway: Standard transformer-style neural network head
|
||||
Quantum Pathway:
|
||||
|
||||
Dimensionality reduction: 768D → 8D (quantum space)
|
||||
Two quantum circuit layers with parameterized gates
|
||||
Quantum-to-vocabulary mapping: 8D → 50K vocab
|
||||
|
||||
|
||||
Learnable Mixing: Parameter α balances classical vs quantum contributions
|
||||
|
||||
Quantum Circuit Design
|
||||
|
||||
8 qubits with 3 parameterized layers
|
||||
RY rotation gates for classical data encoding
|
||||
CNOT gates creating entanglement patterns
|
||||
Pauli-Z measurements for classical output extraction
|
||||
|
||||
Installation & Setup
|
||||
Prerequisites
|
||||
bash# Install dependencies
|
||||
bash
|
||||
# Install dependencies
|
||||
pip install -r requirements.txt
|
||||
|
||||
# Atropos framework (follow official guide)
|
||||
Environment Setup
|
||||
bashexport ATROPOS_HERMES_API_KEY="your-nous-research-api-key"
|
||||
bash
|
||||
export ATROPOS_HERMES_API_KEY="your-nous-research-api-key"
|
||||
Quickstart
|
||||
Basic Training
|
||||
bashpython atropos.py process
|
||||
bash
|
||||
python atropos.py process
|
||||
View Results
|
||||
Monitor training at: https://wandb.ai/your-username/atropos-environments_hack0_env_quant
|
||||
|
||||
Custom Configuration
|
||||
bashpython atropos.py process \
|
||||
bash
|
||||
python atropos.py process \
|
||||
--env.n_qubits 16 \
|
||||
--env.n_layers 5 \
|
||||
--env.total_steps 100 \
|
||||
--env.quantum_weight 0.5
|
||||
Environment Design & Motivation
|
||||
Why Quantum-Classical Hybrid?
|
||||
|
||||
Pattern Recognition: Quantum circuits may capture linguistic patterns that classical networks miss
|
||||
Entanglement: Natural language has complex interdependencies that quantum entanglement might model better
|
||||
Optimization Landscape: Quantum interference could provide novel optimization pathways
|
||||
Knowledge Distillation: Transfer capabilities from large models (Hermes-3-70B) to smaller quantum-enhanced models
|
||||
|
||||
Training Strategy
|
||||
The environment employs quantum-enhanced knowledge distillation:
|
||||
|
||||
|
|
@ -60,23 +59,109 @@ Teacher Model: Hermes-3-70B generates diverse, high-quality responses
|
|||
Student Model: Hybrid quantum-classical model learns next-word prediction
|
||||
Comparison: Direct evaluation of quantum vs classical pathways within the same model
|
||||
Optimization: Both classical and quantum parameters trained via gradient descent
|
||||
|
||||
Results & Metrics
|
||||
Live Experiment
|
||||
🚀 View our latest run: WandB Dashboard: https://wandb.ai/quaintanceai-nous/atropos-environments_hack0_env_quant?nw=nwuserquaintanceai
|
||||
🚀 View our latest run: WandB Dashboard
|
||||
|
||||
Key Metrics Explained
|
||||
Training Metrics
|
||||
|
||||
train/hybrid_loss: Combined quantum-classical model loss
|
||||
train/classical_loss: Baseline classical-only model loss
|
||||
train/quantum_loss: Quantum-specific loss component
|
||||
train/alpha_value: Mixing parameter (0 = full quantum, 1 = full classical)
|
||||
|
||||
Evaluation Metrics
|
||||
|
||||
eval/hybrid_performance: Entropy-based comparison of hybrid vs classical predictions
|
||||
eval/quantum_weight: Current quantum contribution (1 - α)
|
||||
train/quantum_coherence: Measure of quantum circuit effectiveness
|
||||
Model Metrics
|
||||
model/alpha: Real-time mixing parameter
|
||||
model/quantum_contribution: Percentage of quantum influence
|
||||
Interpretation Guide
|
||||
Decreasing hybrid_loss: Model improving at next-word prediction
|
||||
Stable alpha_value: Balanced classical-quantum integration
|
||||
High quantum_coherence: Quantum circuits contributing meaningfully
|
||||
hybrid_performance > 0.5: Quantum enhancement provides benefits
|
||||
Technical Implementation
|
||||
Quantum Circuit Architecture
|
||||
python
|
||||
# Data encoding
|
||||
qml.RY(classical_data, wires=qubit)
|
||||
|
||||
# Parameterized layers
|
||||
for layer in range(n_layers):
|
||||
for qubit in range(n_qubits):
|
||||
qml.RY(learnable_params[layer, qubit], wires=qubit)
|
||||
|
||||
# Entanglement pattern
|
||||
for i in range(n_qubits - 1):
|
||||
qml.CNOT(wires=[i, i + 1])
|
||||
qml.CNOT(wires=[n_qubits - 1, 0]) # Ring topology
|
||||
|
||||
# Measurement
|
||||
[qml.expval(qml.PauliZ(i)) for i in range(n_qubits)]
|
||||
Training Process
|
||||
Forward Pass: Hidden states → quantum circuits → predictions
|
||||
Loss Calculation: Cross-entropy on next-word prediction
|
||||
Backpropagation: Gradients through quantum circuits via parameter-shift rule
|
||||
Optimization: Adam optimizer updates both classical and quantum parameters
|
||||
Current Limitations
|
||||
Simulated Quantum: Uses classical simulation (no quantum hardware)
|
||||
Synthetic Features: Uses random hidden states (not real text embeddings)
|
||||
Scale: Limited to 8 qubits due to exponential simulation cost
|
||||
Evaluation: Simple entropy comparison (more sophisticated metrics possible)
|
||||
Research Impact & Applications
|
||||
Novel Contributions
|
||||
First quantum-enhanced Atropos environment
|
||||
Hybrid architecture balancing quantum and classical processing
|
||||
Knowledge distillation from large classical models to small quantum models
|
||||
Quantum-aware evaluation metrics for NLP tasks
|
||||
Potential Applications
|
||||
Quantum NLP research with differentiable quantum circuits
|
||||
Hybrid model architectures for resource-constrained environments
|
||||
Novel optimization techniques combining classical and quantum approaches
|
||||
Benchmark creation for quantum machine learning in language tasks
|
||||
Future Research Directions
|
||||
Immediate Improvements
|
||||
Real Text Processing: Replace synthetic hidden states with actual transformer embeddings
|
||||
Advanced Quantum Circuits: Implement quantum attention mechanisms
|
||||
Scaling Studies: Investigate qubit count vs performance relationships
|
||||
Long-term Goals
|
||||
Quantum Hardware: Deploy on IBM Quantum, IonQ, or other quantum computers
|
||||
Larger Models: Scale to 100+ qubit systems when available
|
||||
Quantum Advantage: Identify specific NLP tasks where quantum provides provable benefits
|
||||
Production Systems: Develop practical quantum-enhanced language models
|
||||
Repository Structure
|
||||
/environments/hack0/env_quant/
|
||||
├── atropos.py # Main environment implementation
|
||||
├── requirements.txt # Python dependencies
|
||||
├── README.md # This documentation
|
||||
├── quantum_hybrid_artifacts.tar.gz # Training artifacts
|
||||
└── data/
|
||||
└── groups_22.jsonl # Latest training data
|
||||
Contributing
|
||||
We welcome contributions! Areas of particular interest:
|
||||
|
||||
Novel quantum circuit architectures for NLP
|
||||
Advanced evaluation metrics for quantum language models
|
||||
Hardware integration and optimization
|
||||
Theoretical analysis of quantum advantages in language modeling
|
||||
Citation
|
||||
bibtex
|
||||
@software{quantum_hybrid_atropos,
|
||||
title={Quantum-Classical Hybrid Language Model Environment for Atropos},
|
||||
author={QuaintanceAI Research Team},
|
||||
year={2025},
|
||||
url={https://github.com/anthropics/atropos/tree/main/environments/hack0/env_quant},
|
||||
note={Atropos Hackathon 2025 Submission}
|
||||
}
|
||||
License
|
||||
This project is licensed under the MIT License - see the Atropos LICENSE file for details.
|
||||
|
||||
Acknowledgments
|
||||
Anthropic for the Atropos framework and hackathon opportunity
|
||||
Xanadu for PennyLane quantum computing library
|
||||
Nous Research for Hermes-3-70B API access
|
||||
Weights & Biases for experiment tracking
|
||||
PyTorch for automatic differentiation through quantum circuits
|
||||
This environment represents cutting-edge research in quantum machine learning for NLP. While quantum advantages are still under investigation, the framework provides a foundation for future breakthroughs in quantum-enhanced language processing.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue