Re:GPT-4
by geysersam on Tuesday March 14, 2023 @07:32PM
(#35161090)
Is the Reformer as capable as this model? It's a trade-off.
[ Parent
| on HN ]
It's not, it uses locality-sensitive hashing to reduce attention complexity from O(n^2) to O(nlogn) while maintaining the same performance in 16GB as a best model that could fit into 100GB but nobody scaled it up to 1000 GPUs as its purpose was the opposite.