ServiceNow, Hugging Face, and NVIDIA have joined forces to introduce StarCoder2, a family of open-access large language models (LLMs) designed for code generation. This collaborative effort aims to set new standards in performance, transparency, and cost-effectiveness within the realm of generative AI.
Empowering Developers with Enhanced Code Generation Capabilities
StarCoder2, developed by the BigCode community, a collaboration stewarded by ServiceNow and Hugging Face, offers developers a suite of advanced tools for code generation. Trained on a vast array of programming languages, StarCoder2 models can be further customized and integrated into enterprise applications to perform specialized tasks such as source code generation, workflow creation, text summarization, and more. These capabilities are poised to accelerate innovation and improve productivity across various industries.
Model Variants and Performance
StarCoder2 is available in three model sizes, each offering powerful performance tailored to different compute requirements. These variants include a 3 billion-parameter model developed by ServiceNow, a 7 billion-parameter model by Hugging Face, and a 15 billion-parameter model by NVIDIA, leveraging NVIDIA NeMo and trained on NVIDIA accelerated infrastructure. Despite their varying sizes, these models deliver impressive performance, with the 3 billion-parameter model matching the capabilities of the original 15 billion-parameter model.
Advancing Responsible AI Practices
The collaborative effort underscores a commitment to responsible AI practices, ensuring transparency and accountability in model development. Harm de Vries, lead of ServiceNow’s StarCoder2 development team, highlighted the significance of open scientific collaboration and ethical data practices in advancing generative AI capabilities.
Fostering Open Scientific Collaboration
BigCode, led jointly by Hugging Face and ServiceNow, fosters open scientific collaboration in the development of LLMs for code. Through transparent governance and the utilization of responsibly sourced data, BigCode aims to drive innovation while upholding ethical standards in AI development.
Support for Industry-Specific Applications
StarCoder2 models can be fine-tuned with industry or organization-specific data, further enhancing their capabilities for specialized tasks. Organizations have already leveraged the foundational StarCoder model to create task-specific capabilities tailored to their business needs, demonstrating the versatility and applicability of generative AI in various domains.
Availability and Accessibility
StarCoder2 models will be made available under the BigCode Open RAIL-M license, ensuring royalty-free access and use for developers. Additionally, the models will be accessible for download from Hugging Face and NVIDIA platforms, enabling developers to experiment with them directly or through API endpoints.
About ServiceNow, Hugging Face, and NVIDIA
ServiceNow is a leading digital workflow company focused on digitizing and unifying organizations to enhance productivity and innovation. Hugging Face is a prominent open-source platform enabling collaboration in the machine learning community. NVIDIA is a pioneer in accelerated computing, reshaping industries with its data center-scale offerings.