CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.

CodeGemma has 3 model variants:

  • A 7B pretrained variant that specializes in code completion and generation from code prefixes and/or suffixes
  • A 7B instruction-tuned variant for natural language-to-code chat and instruction following
  • A state of the art 2B pretrained variant that provides up to 2x faster code completion
  • CodeGemma models have several advantages:

  • Complete lines, functions, and even generate entire blocks of code, whether you're working locally or using Google Cloud resources.
  • Trained on 500 billion tokens of primarily English language data from web documents, mathematics, and code, CodeGemma models generate code that's not only more syntactically correct but also semantically meaningful, reducing errors and debugging time.
  • Supports Python, JavaScript, Java, Kotlin, C++, C#, Rust, Go, and other languages.
  • Integrate a CodeGemma model into your development environment to write less boilerplate and focus on interesting and differentiated code that matters, faster.

More resources

CodeGemma's model card contains detailed information about the model, implementation information, evaluation information, model usage and limitations, and more.
View more code, Colab notebooks, information, and discussions about CodeGemma on Kaggle.