Aleph Alpha 发布开源权重模型 Kolibri，主打欧洲 AI 主权
Aleph Alpha releases Kolibri, an open-weight model that makes the case for European AI sovereignty
Aleph Alpha 发布 Kolibri，这是一个 78B 参数的德英双语模型，采用混合专家架构，每个 token 约激活 3B 参数。公司称其在两种语言的质量与运行成本上处于帕累托前沿，训练数据中德语占 21.3%，并建有专门的德语数据管线，部分合成数据由中文模型生成。Kolibri 面向公共管理、航空和工业场景，按欧洲法律并参照 EU AI Act 开发，支持最高 100 万 token 上下文窗口，在德国和芬兰的 768 块 B200 GPU 上训练，权重以 Apache 2.0 许可在 Hugging Face 开放。
推荐理由
AI 评分 63
原文给出 Kolibri 的参数量、MoE 激活规模与训练数据构成，可据此判断欧洲主权模型在德语场景的取舍。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Aleph Alpha has released Kolibri, a German-English language model with 78 billion parameters, about three billion of which are active per token through a mixture-of-experts architecture. Aleph Alpha claims Kolibri sits on the Pareto front of quality and operating cost in both languages, outperforming compared models with similar architectures, some significantly older (March, April 2026), on either metric. German accounts for 21.3 percent of the training data, backed by a dedicated German data pipeline the company built for the project. Chinese models were also used to generate synthetic training data.
Aleph Alpha says Kolibri targets public administration, aviation, and industry. The model was developed under European law with the EU AI Act in mind, supports context windows of up to one million tokens, and was trained on 768 B200 GPUs in Germany and Finland, according to the tech report . The weights are available under an Apache 2.0 license on Hugging Face .