Why does a 1B parameter model have a 29GB weights file?

#20

by narai - opened 15 days ago

narai

15 days ago

This weights file is approx 10 times larger than normal for this parameter count. What is the explanation?

narai changed discussion status to closed 15 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment