CodeGemma: Open Code Models Based on Gemma
CodeGemma Team, Zhao, Heri, Hui, Jeffrey, Howland, Joshua, Nguyen, Nam, Zuo, Siqi, Hu, Andrea, Choquette-Choo, Christopher A., Shen, Jingyue, Kelley, Joe, Bansal, Kshitij, Vilnis, Luke, Wirth, Mateo, Michel, Paul, Choy, Peter, Joshi, Pratik, Kumar, Ravin, Hashmi, Sarmad, Agrawal, Shubham, Gong, Zhitao · arXiv (Cornell University) · 2024
This paper introduces CodeGemma, a collection of specialized open code models built on top of Gemma, capable of a variety of code and natural language generation tasks. We release three model variants. CodeGemma 7B pretrained (PT) and instruction-tuned (IT) variants have remarkably resilient natural language understanding, excel in mathematical reasoning, and match code capabilities of other open models. CodeGemma 2B is a state-of-the-art code completion model designed for fast code infilling and open-ended generation in latency-sensitive settings.