ModelsOct 4, 2026 · 04:097 sources

Aleph Alpha's Kolibri AI Uses 21% German Data for EU Compliance

From marketbrief.now

Image: marketbrief.now
AI;DR

Aleph Alpha's Kolibri AI model uses 21.3% German data in its pre-training tokens to comply with EU regulations including the GDPR and the General-Purpose AI Code of Practice. The model uses a mixture-of-experts architecture with 78B total parameters, 3.46B active, and supports a 1M token context window under an Apache 2.0 license. Researchers noted the model was fine-tuned on synthetic data from Chinese models GLM and Qwen.

Read the sourceSign in to suggest

Sources

+ 5 more
  1. SUPPORT@testingcatalog“focused on including organic German data throughout the training process of the model, so that 21.3% of the pre-training tokens are German”x.com
  2. SUPPORT@emollick“Europe's new “sovereign model” is fine-tuned on data generated by… GLM and Qwen”x.com
  3. SUPPORT@clementdelangue“Small bird, fast wings, Kolibri is here.”x.com
  4. SUPPORT@aidangomez“Congrats to the AlephAlpha team on a very cool German-English model”x.com
  5. SUPPORT@cohere“New Apache 2.0 model from @Aleph__Alpha. It's really good.”x.com
#regulationMarkdown
Content history (1)
  • 2026-10-04 · Summary · vi · Wording fix
    Phòng thí nghiệm nghiên cứu AI Đức đã thiết kế mô hình mới nhất tuân thủ Bộ quy tắc Thực …
    Phòng thí nghiệm nghiên cứu AI Đức đã thiết kế mô hình mới nhất tuân thủ Bộ quy tắc Thực …

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today