Cerebras Blog company blog

GigaGPT: GPT-3 sized models in 565 lines of code

GigaGPT is Cerebras’ implementation of Andrei Karpathy’s nanoGPT – the simplest and most compact code base to train and fine-tune GPT models.
Points
223
HN comments
65
Submissions
1
Cited by
0 commenters

AI & Machine LearningSoftware Engineering2023

On Hacker News

SubmittedTitle on HNPointsComments
Dec 11, 2023GigaGPT: GPT-3 sized models in 565 lines of code by georgehill22365

More from Cerebras Blog

All 2 posts →

Related posts from the same era