Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Attention IS NOT all u need
(github.com/Elgoghel)
3 points
Elgoghel
2 months ago
discuss
2.
▲
A 164-parameter architecture beats a 6.5M transformer on SCAN by 94 points
(github.com/Elgoghel)
2 points
Elgoghel
2 months ago
discuss