StarCoder2

StarCoder2 is an open-source code generation model developed by the BigCode project, a collaboration between Hugging Face and ServiceNow. Available in 3B, 7B, and 15B parameter sizes, StarCoder2 was trained on The Stack v2, one of the largest open code training datasets encompassing over 600 programming languages. The model supports a 16K context window and is released under an OpenRAIL-M license that permits commercial use, making it a popular foundation for fine-tuned coding assistants.

Threads