Skip to content

(Beginner) Importing never_split_tokens #189

Answered by WissamAntoun
YomnaEid asked this question in Q&A
Discussion options

You must be logged in to vote

this is because you are using a very old version of the training scripts , this has now been updated to

from arabert.preprocess import NEVER_SPLIT_TOKENS

You also shouldn't need to import any of these tokens if you are doing fine-tuning with arabert

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by YomnaEid
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