I’ve been talking to mamba (the new SSM which a transformer alternative that might scale better) and it has a different feel than base models using transformers, I’m not sure how to characterize…
Posters: UnderwaterBepis. UnderwaterBepis
3 likes recorded by the source corpus.
View Post: https://x.com/UnderwaterBepis/status/1732561539322860019