Re:Ultra Fast Bert
by theGnuMe on Wednesday November 22, 2023 @11:46AM
(#38381602)
There's another paper replacing attention with FF networks so just combine the two and you've got something.
[ Parent
| on HN ]
Link? Sounds like a good read! :)
Not op but might be this: https://arxiv.org/pdf/2311.10642.pdf