SoTaNa: The Open-Source Software Development Assistant

TL;DR

SoTaNa is an open-source software development assistant that fine-tunes LLaMA with instruction data generated by ChatGPT, enabling effective software engineering support on a single GPU.

Contribution

It introduces a parameter-efficient fine-tuning method for open-source models using ChatGPT-generated data, improving software engineering tasks like answering Stack Overflow questions.

Findings

Effective in answering Stack Overflow questions

Capable of code summarization and generation

Operates on a single GPU

Abstract

Software development plays a crucial role in driving innovation and efficiency across modern societies. To meet the demands of this dynamic field, there is a growing need for an effective software development assistant. However, existing large language models represented by ChatGPT suffer from limited accessibility, including training data and model weights. Although other large open-source models like LLaMA have shown promise, they still struggle with understanding human intent. In this paper, we present SoTaNa, an open-source software development assistant. SoTaNa utilizes ChatGPT to generate high-quality instruction-based data for the domain of software engineering and employs a parameter-efficient fine-tuning approach to enhance the open-source foundation model, LLaMA. We evaluate the effectiveness of \our{} in answering Stack Overflow questions and demonstrate its capabilities. Additionally, we discuss its capabilities in code summarization and generation, as well as the impact of varying the volume of generated data on model performance. Notably, SoTaNa can run on a single GPU, making it accessible to a broader range of researchers. Our code, model weights, and data are public at \url{https://github.com/DeepSoftwareAnalytics/SoTaNa}.