CodeGemma: Open Code Models Based on Gemma

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...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Team, CodeGemma, Zhao, Heri, Hui, Jeffrey, Howland, Joshua, Nguyen, Nam, Zuo, Siqi, Hu, Andrea, Choquette-Choo, Christopher A, Shen, Jingyue, Kelley, Joe, Bansal, Kshitij, Luke Vilnis, Wirth, Mateo, Michel, Paul, Choy, Peter, Joshi, Pratik, Kumar, Ravin, Hashmi, Sarmad, Agrawal, Shubham, Gong, Zhitao, Fine, Jane, Warkentin, Tris, Ale Jakse Hartman, Ni, Bin, Korevec, Kathy, Schaefer, Kelly, Huffman, Scott
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 19.06.2024
Subjects
Building codes
Speech recognition
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422