2000 character limit reached
CodeGemma: Open Code Models Based on Gemma (2406.11409v2)
Published 17 Jun 2024 in cs.CL and cs.AI
Abstract: 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.
- CodeGemma Team (1 paper)
- Heri Zhao (1 paper)
- Jeffrey Hui (6 papers)
- Joshua Howland (5 papers)
- Nam Nguyen (46 papers)
- Siqi Zuo (3 papers)
- Andrea Hu (3 papers)
- Christopher A. Choquette-Choo (49 papers)
- Jingyue Shen (3 papers)
- Joe Kelley (2 papers)
- Kshitij Bansal (12 papers)
- Luke Vilnis (20 papers)
- Mateo Wirth (10 papers)
- Paul Michel (27 papers)
- Peter Choy (4 papers)
- Pratik Joshi (7 papers)
- Ravin Kumar (10 papers)
- Sarmad Hashmi (1 paper)
- Shubham Agrawal (21 papers)
- Zhitao Gong (12 papers)