KoBERT-LM

• Further pretrained model for re-training LM Mask Head

How to use

If you want to import KoBERT tokenizer with AutoTokenizer, you should give trust_remote_code=True.

from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("monologg/kobert-lm")
tokenizer = AutoTokenizer.from_pretrained("monologg/kobert-lm", trust_remote_code=True)

Reference

• https://github.com/SKTBrain/KoBERT