13 points | by E-Reverance an hour ago
2 comments
It makes sense to me that distributing across more parameters results in models that can be quant more heavily (information theory - more bits available)
Anyone with a billion dollars want to try this and report back?
It makes sense to me that distributing across more parameters results in models that can be quant more heavily (information theory - more bits available)
Anyone with a billion dollars want to try this and report back?