It is a good approach to promote it as a German model. But I wonder if it really thinks like the German think. I speculate they just translated texts in other languages, likely English and Chinese, into German.
Hey, I worked on pre-training data Kolibri. We spent considerable time and effort to go beyond just translating. For example by building a pipeline that processes Common Crawl dumps specifically for German. You might be interested in a related blog post: <a href="https://aleph-alpha.com/en/blog/sauerkraut-not-burgers-why-german-llms-need-german-data/" rel="nofollow">https://aleph-alpha.com/en/blog/sauerkraut-not-burgers-why-g...
We also talk more about German pre-training data in the tech report: <a href="https://aleph-alpha.com/downloads/tech-report.pdf" rel="nofollow">https://aleph-alpha.com/downloads/tech-report.pdf section 2.3.2.2.
Lucasoato · · focus · HN ↗
This means that it’s always on time, it uses acronyms for everything and when there’s a decision to be made, it sets up a committee.
sbinnee · · focus · HN ↗
ivo-42 · · focus · HN ↗
We also talk more about German pre-training data in the tech report: <a href="https://aleph-alpha.com/downloads/tech-report.pdf" rel="nofollow">https://aleph-alpha.com/downloads/tech-report.pdf section 2.3.2.2.