News for hackers. Stuff that matters.
Re:Yandex YaLM 100B: Largest GPT-Like Neural Network in Open... by r721 on Sunday December 04, 2022 @09:07AM (#33853810)
Previous discussion: https://news.ycombinator.com/item?id=31846593 (642 comments)
Re:Yandex YaLM 100B: Largest GPT-Like Neural Network in Open... by touringa on Sunday December 04, 2022 @06:29PM (#33859239)
Maybe back in June 2022.

Since then, around 70,000 new Transformer models have been released via HF.

There are several models much larger than YaLM, including BigScience BLOOM 176B and Tsinghua GLM-130B.

https://lifearchitect.ai/timeline/

https://lifearchitect.ai/models/

Re:Yandex YaLM 100B: Largest GPT-Like Neural Network in Open... by redanddead on Monday December 05, 2022 @06:34AM (#33864240)
What's the next big thing in the field?