Google 官方推出 CodeGemma：專為程式碼生成與補全設計的輕量級開源模型
Original: CodeGemma - an official Google release for code LLMs
Google and Hugging Face have jointly announced the launch of CodeGemma, a family of lightweight open-source large language models (LLMs)…
Google 官方正式發布 CodeGemma 程式碼模型系列，基於 Gemma 架構。提供專攻 IDE 程式碼補全（Fill-in-the-Middle）的 2B 版本，以及適合程式碼生成與對話的 7B 版本。該系列模型已深度整合至 Hugging Face 生態系，支援多種主流程式語言，為開發者提供高效且可本地運行的開源 AI 助手選擇。
Google and Hugging Face have jointly announced the launch of CodeGemma, a family of lightweight open-source large language models (LLMs) designed specifically for coding tasks. CodeGemma is based on fine-tuning and additional pretraining of Google's previously released Gemma model architecture, and is intended to give developers powerful yet efficient code assistance tools.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.