this post was submitted on 12 Jun 2024
14 points (100.0% liked)

Programmer Humor

35334 readers
1 users here now

Post funny things about programming here! (Or just rant about your favourite programming language.)

Rules:

founded 6 years ago
MODERATORS
cat_programmer@lemmy.ml
14
If AI can now speak Italian, it can certainly replace us... (sopuli.xyz)
submitted 2 years ago by lseif@sopuli.xyz to c/programmerhumor@lemmy.ml
36 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] PlexSheep@infosec.pub 2 points 2 years ago (1 children)

Do you have a source for that? Seems like an internal detail a corpo wouldn't publish

[–] stingpie@lemmy.world 1 points 2 years ago

Can't find the exact source–I'm on mobile right now–but the code for the gpt-2 encoder uses a utf-8 to unicode look up table to shrink the vocab size. https://github.com/openai/gpt-2/blob/master/src/encoder.py