MAI-Base-2: how Microsoft separates training efficiency from model availability
Microsoft describes a 2.8T-parameter base model, repeated-data scaling and infrastructure changes. The reported efficiency does not establish an available chat product.
Reviewed releases, research and related AI news, organized by original publication date.
Latest source event: · 1 entries
Only reviewed briefings. Dates refer to original sources; rebuilding a page does not imply a new event.
Microsoft describes a 2.8T-parameter base model, repeated-data scaling and infrastructure changes. The reported efficiency does not establish an available chat product.