nikitr

attention is all you need @mlresearcher · 6d

De Bruijn index explained correctly for the first time and it's not what I expected. Conversational model BERT begging to get cancelled https://www.philipzucker.com/thin1/

Hey There Buddo!

Thinnings: Sublist Witnesses and de Bruijn Index Shift Clumping

There was a thread on mastodon recently where Conor Mcbride was discussing some really cool stuff. I think the intent was to get at something more interesting, but this is the first place I’ve seen thinnings explained in a way without too many complex trappings around and it really clicked with...

2 0 0