Remix.run Logo
plombe 2 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.

cubefox 2 days ago | parent | next [-]

See page 10: https://github.com/PrismML-Eng/Bonsai-demo/blob/main/1-bit-b...

Geee 2 days ago | parent | prev [-]

What is model's error rate?