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.
It’s not a dupe, it’s a full training and infra report
dang 1 minutes ago [-]
The criterion for a dupe is not whether the url is identical, it's whether the two different submissions can support a substantially different discussion.
The report is certainly useful! but there is no way that the discussions would remain partitioned, with one thread about the model in general and another thread about this report in particular.
Therefore the two submissions are dupes and the solution is to include a link to the report from the other one. I've put that in the toptext there now, and will merge the comments.
Rendered at 21:31:04 GMT+0000 (Coordinated Universal Time) with Vercel.
> 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
The report is certainly useful! but there is no way that the discussions would remain partitioned, with one thread about the model in general and another thread about this report in particular.
Therefore the two submissions are dupes and the solution is to include a link to the report from the other one. I've put that in the toptext there now, and will merge the comments.