News for hackers. Stuff that matters.
Re:GPT4 is 8 x 220B params = 1.7T params by HarHarVeryFunny on Wednesday June 21, 2023 @06:52AM (#36416896)
The rumor here is that GPT-4 isn't one giant model, but instead a "mixture of experts" combination of 8 smaller GPT-3 sized models with different training sets.

This has implications for what may be possible on consumer hardware.

There are no comments on this comment yet.