The Sequence AI of the Week #899: Inside Inkling: A Trillion-Parameter Model That Only Wakes Up 41 Billion at a Time
Thinking Machine's new model revitalizes America's open source AI approach.
TL;DR
- Inkling has 975 billion parameters, but only 41 billion are active per token.
- This makes the arithmetic sparse, improving efficiency.
- The model is compared to a university with many specialist departments, where only a few are selected for each task.
- The selection of specialists is dynamic, based on the input (e.g., text in different languages, audio, or diagrams).