HackerTrans
TopNewTrendsCommentsPastAskShowJobs

bitRAKE

no profile record

comments

bitRAKE
·3 года назад·discuss
The early exit can be done without an extra flag, but increased code size.
bitRAKE
·3 года назад·discuss
Long term is fuzzy, but the 3D chip tech seems poised to offer exactly that: massive cache, GPU and CPU cores. NVidia isn't going to play nice because they don't like where this positions them in this future. AMD, Intel and Apple don't seem to need NVidia. This tension is bad for end-users.
bitRAKE
·3 года назад·discuss
The 1.4T tokens are what the model was trained on, and not the token range of the embedding.