1 comment

[ 4.4 ms ] story [ 15.1 ms ] thread
Genuine link: https://arxiv.org/pdf/2306.02707.pdf

HN apparently won't let duplicate posts and since the first submission didn't really gain any traction thought I'd resubmit a video version of it so people catch up with what is most likely the state of the art in open source. As stated in the papper MS is going to release the model in a similar manner to llama, so this is definitely exciting news for many.