Open Horikitasaku opened 4 months ago
I'm not sure why the author commented the cls But I think it's a bug Please let me know if I'm wrong.
My idea is that since the model has the ability to fine-tune downstream classification tasks, we should keep the [CLS].
The code in tokenizer
has a bug, it seem to be missing the [CLS]
the code in huggingface is
but I think it should be
according to the code from github