Thinking Machines releases Inkling Small with Inkling-level results at a fraction of the compute

IT News

Friday at 18:42

13 Visningar

0 Kommentarer

$Thinking Machines releases Inkling Small with Inkling-level results at a fraction of the compute$

Thinking Machines has released Inkling Small, a 276-billion-parameter open-weights model that activates only 12 billion parameters per token. The smaller Mixture-of-Experts model nearly matches its 975-billion-parameter sibling while exceeding it on several reasoning and coding benchmarks. Source

Läs hela artikeln hos källan.

Läs originalartikeln

Delta i diskussionen — kommentera, rösta och dela länkar.

Registrera