Skip to content

Anyway cyrillic support? #69

Closed Answered by LostRuins
aga7on asked this question in Q&A
Apr 15, 2023 · 1 comments · 1 reply
Discussion options

You must be logged in to vote

It is common that non-english text takes up significantly more tokens on most English focused models. You'd have to find a model that was trained specifically for multilingual text. It has nothing to do with the inference software

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@aga7on
Comment options

Answer selected by aga7on
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants