why in makemore2.jl does the loss bottom out at 4? the same code written with torch and flux consistently hits ~2.5ish
todo: build bigram word model on the concatenated yt transcripts
-
Notifications
You must be signed in to change notification settings - Fork 1
anandijain/nn_zero_to_hero
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published