Cornell U & Google Brain’s FLASH Yields High Transformer Quality in Linear Time

A research team from Cornell University and Google Brain introduces FLASH, a model family that achieves quality on par with fully augmented transformers while maintaining linear scalability over th...

By · · 1 min read

Source: syncedreview.com

A research team from Cornell University and Google Brain introduces FLASH, a model family that achieves quality on par with fully augmented transformers while maintaining linear scalability over the context size on modern accelerators.