SoTaNa: The Open-Source Software Development Assistant

08/25/2023
by   Ensheng Shi, et al.
0

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 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 <https://github.com/DeepSoftwareAnalytics/SoTaNa>.

READ FULL TEXT
research
06/14/2023

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Code Large Language Models (Code LLMs), such as StarCoder, have demonstr...
research
04/11/2023

Evaluating AIGC Detectors on Code Content

Artificial Intelligence Generated Content (AIGC) has garnered considerab...
research
04/03/2023

Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data

Chat models, such as ChatGPT, have shown impressive capabilities and hav...
research
08/06/2023

LARCH: Large Language Model-based Automatic Readme Creation with Heuristics

Writing a readme is a crucial aspect of software development as it plays...
research
10/06/2018

Gendered behavior as a disadvantage in open source software development

Women are severely marginalized in software development, especially in o...
research
07/08/2023

Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators

Large language models that exhibit instruction-following behaviour repre...
research
09/18/2023

An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models

Visual instruction tuning has recently shown encouraging progress with o...

Please sign up or login with your details

Forgot password? Click here to reset