“That came out from one of our principal research…” — Practical AI at 14:08
“That came out from one of our principal research scientists, Dan Alistar, called SparseGPT. And that's where we're looking at taking OPT and Bloom models all the way up to 175 billion parameters and being able to optimize those and remove as many weights as possible, all in this case in one shot. So just using the…”
0:00
38:28