arXiv 自然语言处理· Aleph Alpha, :, Moritz Althaus, Artur Baranowski, Michael Barlow, Fabien C. Y. Benureau, Felix Berkenkamp, Amrita Bhattacherjee, Lukas Bl\"ubaum, Duncan Blythe, Augustijn de Boer, Bastian Boll, Thomas F. Burns, Bj\"orn Deiseroth, Niko D\"urr, B\'eni Bal\'azs Egressy, Niklas Finken, Niklas Freymuth, Fabian Gebhart, Max Hammer, Bastian Harren, Andreas Hartel, Johann Higl, Steffen Hirschmann, Pablo Iyu Guerrero, Yasser Jadidi, Andreas Jagusch, Mitja Kleider, Markus Klein, Jonas Knupp, Murali Kondragunta, Garwin Lechner, Dominik L\^e-Kellner, Jurek Leonhardt, Jiaze Li, Sohir Maskey, Omar Mehio, Pit Neitemeier, Letitia Parcalabescu, Alejandro Petry Pacheco, Pranav Ragupathy, Martin Reinhardt, Peter Rodenkirch Nfissi, Dylan Rodriquez, Leonard Salewski, Raziye Sari, Jordan Sassoon, Ivo Schaper, Ilhan Scheer, Frank Schneider, Philipp Scholl, Lukas Schott, Eric Schreiber, Pablo Schumacher, Alessio Serra, Philipp Siedler, Prabhu Teja Sivaprasad, Mohamed Soliman, Till Speicher, Volker Stampa, Simon Thel, Serge Thilges, Irina Vidal Migall\'on, Denis Wa{\ss}mann, Samuel Weinbach, Sascha Wirges, Michael W\"uthrich, Alexei Zacharov·· 5 小时前AI 评分62
Aleph Alpha 开源欧洲主权大模型 Kolibri
Kolibri: A Sovereign European Model on the Pareto Frontier
AI 导读
Aleph Alpha 正式开源英德双语 MoE 大模型 Kolibri 权重，采用 Apache 2.0 许可证。该模型总参数量为 78.1B，每个 token 激活参数仅 3.46B，在包含超 20% 德语数据的 24T tokens 上完成全流程训练。其后训练结合了 SFT 与覆盖推理、代码、工具调用等超 1.2M 项内部任务的强化学习，旨在满足公共管理与工业等受监管领域的低成本部署需求。
来源：arXiv 自然语言处理 · arxiv.org