zookini

Karma: 1

zookini 18 Nov 2024 1:33 UTC
1 point
0
on: Redundant Attention Heads in Large Language Models For In Context Learning
each previous example confirming the pattern attends to the $i$ th example, and adds a constant update term (equivilant to $log (c) + n o r m$ ) to the $i$ th example.
Nit: should be \log(c) - norm

zookini 14 Apr 2024 9:58 UTC
2 points
0
on: The Best Tacit Knowledge Videos on Every Subject
Tacit knowledge videos for CAD modelling:
https://www.youtube.com/playlist?list=PLzMIhOgu1Y5fwotlIEKNnuIXcEbVIZ7Qm