BigCode: Open and responsible development of LLMs for code
Welcome to the AI research bites. This series of short and informative talks showcases cutting-edge research work from ServiceNow AI Research team. The AI Research Bites are open to all, especially those interested in keeping up with the fast-paced AI research community.
This session will feature Raymond Li's work on BigCode, an open scientific collaboration working on the responsible development and use of large language models for code. This collective led by ServiceNow and Hugging Face recently released the second iteration of the StarCoder family of models and TheStack dataset all under permissive licenses.
The first StarCoder release powers ServiceNow's text-to-code & text-to-flow capabilities in Now Assist! And the second iteration was released on February 29th 2024.
StarCoder2 page on Hugging Face: https://huggingface.co/docs/transformers/main/model_doc/starcoder2
StarCoder2 tech report: https://arxiv.org/abs/2402.19173
BigCode website: https://www.bigcode-project.org/
Using StarCoder to generate structured outputs: https://arxiv.org/pdf/2404.08189
ServiceNow AI Research team: https://www.servicenow.com/research/