Stability AI has announced the release of Stable Code 3B, an upgraded three billion parameter AI system for automatic code generation and completion.
With enhancements like larger context size and improved completion quality, Stable Code 3B aims to push the boundaries of AI-assisted software development.
At just three billion parameters, Stable Code 3B is designed to run efficiently on readily available hardware like laptops—unlike larger models which require expensive specialised chips. Despite its smaller size, the company claims it matches or exceeds the code completion quality of models over twice its size.
The system builds on Stability AI’s Stable LM natural language model with additional training on software engineering data like code repositories and programmer forums. It covers 18 programming languages including Python, JavaScript, Java, C++, and Go.
The model’s training process witnessed optimisation through the incorporation of Rotary Position Embeddings (RoPE), expanding the context size for improved performance. This technique, also employed by Meta’s Llama 2 Long, allows for context lengths up to 100k tokens.
Beyond simply suggesting new lines of code, it can also fill in large missing sections in existing code. This advanced ability is known as Fill in the Middle (FIM) and allows it to automatically write entire functions or components.
The field of AI-generated code has attracted intense interest from tech giants like Microsoft, OpenAI, and Meta. Stability AI’s new system outperforms comparable models like StarCoder and establishes it as a leader in this fast-moving space:
With impressive benchmarks and increased accessibility from its efficient size, Stable Code 3B aims to bring enhanced AI code completion to a wider audience. Its arrival promises to further accelerate the integration of generative AI into software development workflows across industries.
With systems like Stable Code 3B automating rote coding tasks, developers stand to become more productive, creative, and can focus their efforts on more complex challenges.
(Photo by Joan Gamell on Unsplash)
See also: IMF: AI could boost growth but worsen inequality
Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week and Cyber Security & Cloud Expo.
Explore other upcoming enterprise technology events and webinars powered by TechForge here.
