logoalt Hacker News

skavi • yesterday at 7:12 AM • 1 reply • view on HN

and the repo for this project: https://github.com/microsoft/BitNet

Replies

sinuhe69 • yesterday at 10:02 AM

The demo they showed was full of repeated sentences. The 3B model looks quite dense, TBH. Did they just want to show the speed?

➕ show 1 reply