Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

CodeGemma-2B

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

4K tokens

Max output length

No data

Model type

编程大模型

Release date

2024-04-09

Model file size

5.03GB

MoE architecture

Total params / Active params

20.0B / N/A

Knowledge cutoff

No data

CodeGemma-2B

Open source & experience

Code license

Apache 2.0

Weights license

Gemma Terms of Use- 免费商用授权

GitHub repo

https://github.com/google/gemma_pytorch

Hugging Face

https://huggingface.co/google/codegemma-2b

Live demo

No live demo

CodeGemma-2B

Official resources

Paper

CodeGemma: Open Code Models Based on Gemma

DataLearnerAI blog

No blog post yet

CodeGemma-2B

API details

API speed

No data

No public API pricing yet.

CodeGemma-2B

Benchmark Results

No benchmark data to show.

CodeGemma-2B

Publisher

Google Research

View publisher details

CodeGemma-2B

Model Overview

CodeGemma是Google开源的一系列编程大模型，分为三个版本，CodeGemma-7B、CodeGemma-7B-IT和CodeGemma-2B，第一个模型也成为Gemma-7B-PT，这里的PT代表的是PyTorch，IT代表Instruct，做过指令微调。

CodeGemma-2B是其中20亿参数规模版本，该模型没有指令微调优化的版本。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送