Kodezi Chronos is a debugging-first language model
Kodezi Chronos is a research project focused on developing a specialized language model designed specifically for debugging software and understanding large code repositories. Unlike general-purpose language models that focus primarily on code generation, Chronos is built to diagnose and repair bugs by analyzing complex relationships across files within a codebase. The project introduces architectural techniques such as Adaptive Graph-Guided Retrieval, which allows the system to navigate...
Datasets, tools, and benchmarks for representation learning of code
CodeSearchNet is a large-scale dataset and research benchmark designed to advance the development of systems that retrieve sourcecode using natural language queries. The project was created through collaboration between GitHub and Microsoft Research and aims to support research on semantic code search and program understanding. The dataset contains millions of pairs of sourcecode functions and corresponding documentation comments extracted from open-source repositories. ...