77 points•yu3zhou4•about 3 hours ago•2 comments•

2 comments

senkoabout 1 hour ago
Since it's a PDF, here's an excerpt from the summary:

> This report introduces Kolibri, an English–German Mixture-of-Experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under the Apache 2.0 licence.

> We built Kolibri for sovereign and specialised deployment, with a particular focus on German and on regulated domains such as public administration, industry, and aerospace. To support these settings, we control the full model-development process, including data, architecture, training infrastructure, post-training, and evaluation.

Dupe of https://news.ycombinator.com/item?id=49942706

yu3zhou4about 1 hour ago
It’s not a dupe, it’s a full training and infra report

Read the full thread on Hacker News →

Related stories