Replies: 1 comment 1 reply
-
I think the issue probably comes from here. if model_name in [
"vinai/bertweet-base",
"vinai/bertweet-covid19-base-cased",
"vinai/bertweet-covid19-base-uncased",
]:
self.tokenizer = tokenizer_class.from_pretrained(
model_name,
do_lower_case=self.args.do_lower_case,
normalization=True,
**kwargs,
)
else:
self.tokenizer = tokenizer_class.from_pretrained(
model_name, do_lower_case=self.args.do_lower_case, **kwargs
) A quick fix would be to just add the name of the model you want to use here. I will change this logic later to check for strings matching any Bertweet model. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
I am experimenting with NER, more concretely, the Bertweet model (I saw that simpletransformers supports this model), and I noticed that vinai/bertweet-large does not work. Can you please tell me whether this a bug or this model is not supported? I have tested the other betrtweet models: vinai/bertweet-base, vinai/bertweet-covid19-base-cased, and vinai/bertweet-covid19-base-uncased, and they work properly.
Thank you in advance and I would like to use this opportunity to thank you for the great job you are doing: simpletransformers is an awesome library!
Best regards,
Igor
Beta Was this translation helpful? Give feedback.
All reactions