홈 › Papers

PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generation

2025-07-25 · Abdul Basit, Minghao Shao, Muhammad Haider Asif, Nouhaila Innan, Muhammad Kashif, Alberto Marchisio, Muhammad Shafique arxiv

The growing demand for robust quantum programming frameworks has unveiled a critical limitation: current large language model (LLM) based quantum code assistants heavily rely on remote APIs, introducing challenges related to privacy, latency, and excessive usage costs. Addressing this gap, we propose PennyCoder, a novel lightweight framework for quantum code generation, explicitly designed for local and embedded deployment to enable on-device quantum programming assistance without external API dependence. PennyCoder leverages a fine-tuned version of the LLaMA 3.1-8B model, adapted through parameter-efficient Low-Rank Adaptation (LoRA) techniques combined with domain-specific instruction tuning optimized for the specialized syntax and computational logic of quantum programming in PennyLane, including tasks in quantum machine learning and quantum reinforcement learning. Unlike prior work focused on cloud-based quantum code generation, our approach emphasizes device-native operability while maintaining high model efficacy. We rigorously evaluated PennyCoder over a comprehensive quantum programming dataset, achieving 44.3% accuracy with our fine-tuned model (compared to 33.7% for the base LLaMA 3.1-8B and 40.1% for the RAG-augmented baseline), demonstrating a significant improvement in functional correctness.

📄 PDF Abstract BibTeX arXiv:2507.19562

Code (0)

등록된 구현이 없습니다.

Tasks

Quantum Machine Learning Reinforcement Learning Code Generation

PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset

2025-03-04 · Abdul Basit, Nouhaila Innan, Haider Asif, Minghao Shao 외

Large Language Models (LLMs) offer remarkable capabilities in code generation, natural language processing, and domain-specific reasoning. However, their application in quantum software development remains underexplored,…

Code Generation RAG Retrieval-augmented Generation

PennyLane: Automatic differentiation of hybrid quantum-classical computations

2018-11-12 · Ville Bergholm, Josh Izaac, Maria Schuld, Christian Gogolin 외

PennyLane is a Python 3 software framework for differentiable programming of quantum computers. The library provides a unified architecture for near-term quantum computing devices, supporting both qubit and continuous-va…

BIG-bench Machine Learning Quantum Machine Learning

QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges

2025-06-24 · Abdul Basit, Minghao Shao, Haider Asif, Nouhaila Innan 외

Recent advances in Large Language Models (LLMs) have demonstrated strong potential in code generation, yet their effectiveness in quantum computing remains underexplored. This paper benchmarks LLMs for PennyLane-based qu…

Benchmarking Code Generation RAG Retrieval-augmented Generation

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation

2026-03-25 · Ali Slim, Haydar Hamieh, Jawad Kotaich, Yehya Ghosn 외 arxiv

Large Language Models (LLMs) are increasingly used for code generation, yet quantum code generation is still evaluated mostly within single frameworks, making it difficult to separate quantum reasoning from framework fam…

Code Generation

Introduction to Quantum Reinforcement Learning: Theory and PennyLane-based Implementation

2021-08-16 · Yunseok Kwak, Won Joon Yun, Soyi Jung, Jong-Kook Kim 외

The emergence of quantum computing enables for researchers to apply quantum circuit on many existing studies. Utilizing quantum circuit and quantum differential programming, many research are conducted such as \textit{Qu…

BIG-bench Machine Learning Learning Theory Quantum Machine Learning reinforcement-learning+2