Hacker News new | ask | show | jobs
by plombe 82 days ago
Interesting post. Curious to know how they arrived at intelligence density = Negative log of the model's error rate divided by the model size.
2 comments
cubefox 82 days ago
See page 10: https://github.com/PrismML-Eng/Bonsai-demo/blob/main/1-bit-b...
link
Geee 82 days ago
What is model's error rate?
link