undefined | Better HN

0 pointssub71y ago0 comments

will look into emergent transformers again but I did take cs231n at Stanford and know wtf is up here

0 comments

If it's of any help, it's the multi-head attention mechanism, one of the more unique characteristics (although it can be done in other NN's).

j / k navigate · click thread line to collapse

0 pointssub71y ago0 comments

will look into emergent transformers again but I did take cs231n at Stanford and know wtf is up here

If it's of any help, it's the multi-head attention mechanism, one of the more unique characteristics (although it can be done in other NN's).

j / k navigate · click thread line to collapse