NVIDIA and Microsoft releases 530B parameter transformer model providing further evidence for the scaling hypothesis (~ larger neural nets are smarter) https://www.lesswrong.com/posts/bGuMrzhJdENCo8BxX/nvidia-and-microsoft-releases-530b-parameter-transformer
Links for 2021-10-12
Links for 2021-10-12
Links for 2021-10-12
NVIDIA and Microsoft releases 530B parameter transformer model providing further evidence for the scaling hypothesis (~ larger neural nets are smarter) https://www.lesswrong.com/posts/bGuMrzhJdENCo8BxX/nvidia-and-microsoft-releases-530b-parameter-transformer