德国 Aleph Alpha 发布开源模型 Kolibri：78B 参数、1M 上下文
德国 Aleph Alpha 出了个开源模型 Kolibri，78B 参数激活才 3.46B，上下文 100 万 token，德语数据占两成，欧洲本地化部署可以看看。
德国实验室 Aleph Alpha 发布开源权重模型 Kolibri，总参数 78B、激活参数 3.46B 的 MoE 架构，上下文窗口 1M，采用 Apache 2.0 许可证。模型支持显式推理模式和工具调用，针对长上下文与推理效率优化。训练数据中 21.3% 的预训练 token 为德语，团队还开发了德英双语 tokenizer。模型从设计阶段就遵循 EU AI Act、通用 AI 行为准则和 GDPR。
Aleph Alpha released Kolibri, a 78B-parameter, 3.46B active, MoE open-weight model with 1M context window, distributed under the Apache 2.0 license.
Aleph Alpha is a German AI lab, and it is probably the first general-purpose model from the EU, apart from Mistral, to achieve this level of performance!
> "The model supports an explicit reasoning mode and tool calling. It is optimized for long-context and inference efficiency."
> "The Aleph Alpha team developed a bilingual German/English tokenizer and focused on including organic German data throughout the training process of the model, so that 21.3% of the pre-training tokens are German."
> "Kolibri was built with the EU AI Act, the General-Purpose AI Code of Practice and the GDPR in mind from the ground up, with copyright law being a focus of our work to trustworthy technology."
More EU labs are joining the party 👀
