Aleph Alpha releases Kolibri, a 78B German-English open-weight model under Apache 2.0

The mixture-of-experts model activates 3.46B parameters per token and supports up to 1M tokens of context, per its Hugging Face card.

The mixture-of-experts model activates 3.46B parameters per token and supports up to 1M tokens of context, per its Hugging Face card.