Exciting update: Qiskit Code Assistant service now exposes compatible endpoints with OpenAI Completions API. This enables seamless usage via existing libraries like OpenAI and LiteLLM, making it easy to infuse Qiskit knowledge into your LLM pipelines.
Released granite-8b-qiskit-rc-0.10, the latest revision of the LLMs that empower Qiskit Code Assistant. Trained on significantly expanded Qiskit synthetic dataset, this marks the final model using the current training approach as we pivot to newer Granite base models and cutting-edge techniques.
Shipped granite-8b-qiskit-rc-0.10, the latest revision of LLMs empowering Qiskit Code Assistant. Trained on significantly expanded Qiskit synthetic dataset, marking the end of an era as the final model using current training approach before pivoting to newer Granite base models.
Celebrating qiskit-ibm-transpiler recognition as the 4th most used quantum computing development tool globally in the 2024 Unitary Fund survey. A remarkable achievement for a project with just 1 year of public existence, combining Qiskit heuristic algorithms with novel AI transpiler passes.
Excited to participate in the Quantum Developer Conference 2024 at IBM Thomas J. Watson Research Center, networking with quantum computing professionals and showcasing new developments at the intersection of AI and quantum computing - featuring the Qiskit Code Assistant and AI-powered transpiler passes.
Published a comprehensive blog post summarizing what Qiskit Code Assistant is and how to start using it. Following the recent launch, users are actively leveraging the tool features, and the team is developing improved models with enhanced capabilities for open source release.
Attended IEEE Quantum Week 2024 highlighting four major IBM Quantum AI initiatives: Qiskit Transpiler Service with AI-powered optimization, first preview of Qiskit Code Assistant, unitary compilation research with David Kremer, and the Qiskit HumanEval benchmark presentation.
Presenting the Qiskit HumanEval benchmark for LLMs at IEEE Quantum Week 2024 in the SYS-BNCH Benchmarking session. Available afterwards at the IBM Quantum booth to discuss AI and quantum computing initiatives.
Published research paper on AI methods for approximate compiling of unitaries, accepted at QCE24. The work uses deep learning and autoencoder-like models to enhance quantum circuit transpiling, demonstrating improvements over exhaustive search and random initialization on 2 and 3-qubit unitaries.
Published research paper introducing Qiskit HumanEval dataset for evaluating Large Language Models capability to generate quantum computing code. The dataset comprises more than 100 quantum computing tasks with prompts, solutions, test cases, and difficulty ratings, establishing benchmarks for generative AI tools in quantum code development.