Google Gemma 2 上线 Ollama,提供 2B、9B、27B 三个尺寸
Google Gemma 2 · Ollama Blog
Google Gemma 2 已在 Ollama 上线,提供 2B、9B 和 27B 三个参数尺寸,采用全新架构。Ollama 给出的运行命令为 ollama run gemma2:2b、ollama run gemma2 和 ollama run gemma2:27b,并可与 LangChain、LlamaIndex 等工具配合使用。原文称 27B 版本在基准测试中性能超过参数量两倍于它的模型。
推荐理由
AI 评分 73
Ollama 同步上线 Gemma 2 三个尺寸,读者可据此了解该模型在开源生态中的可用入口与参数规模。
主题
正文
当前显示原文,中文全文译文尚未就绪。
June 27, 2024
Google Gemma 2 is now available in three sizes, 2B, 9B and 27B, featuring a brand new architecture designed for class leading performance and efficiency.
To run Gemma 2:
Class leading performance
At 27 billion parameters, Gemma 2 delivers performance surpassing models more than twice its size in benchmarks. This breakthrough efficiency sets a new standard in the open model landscape.
Three sizes: 2B, 9B and 27B parameters
The initial release of Gemma 2 includes two sizes:
2B Parameters ollama run gemma2:2b; 9B Parameters ollama run gemma2; 27B Parameters ollama run gemma2:27b
Using Gemma 2 with popular tooling
LangChain
LlamaIndex