Aleph Alpha releases Kolibri weights under Apache 2.0
Aleph Alpha’s Kolibri has 78 billion parameters, with 3.46 billion active, and a context window of up to 1 million tokens. The weights are available to run on local hardware under Apache 2.0.
Aleph Alpha’s Kolibri has 78 billion parameters, with 3.46 billion active, and a context window of up to 1 million tokens. The weights are available to run on local hardware under Apache 2.0.
NCP-ArchPreview is released under Apache 2.0. The labs report that, after training on 5.73 trillion Dolma 3 tokens, it matches OLMo-3-7B’s final Stage 1 loss with 51.3% of the tokens, a 1.95× convergence gain.