What I don't understand is why a forward-looking individual such as yourself is not having CatsGTP/Stable Diffusion make all your cards for you.
Several hours la-ter...
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Quote:
|
We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models.... and can reach 60% unstructured sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these models can be ignored at inference time.
|
__________________
.
.Without freedom of speech we wouldn't know who all the idiots are. -- anonymous poster
____________________
.
.What the headline giveth, the last paragraph taketh away. -- Scott Ott
Last edited by freebeard; 05-04-2023 at 02:56 AM..
|