kykim/bert-kor-base

70GB Korean text dataset and 42000 lower-cased subwords are used . Check the model performance and other language models for Korean in GitHub in a new language model . The model is based on BertTokenizerFast, BertModel.from_pretrained("kykim/bert-kor-base") and BertModelModel.model_bert is a language model for Korean. The model was trained on a 70GB text dataset with 42,000 subwords and a total of 7,000 Korean words. It is a Korean language language model that has been used in the model. It has been developed in the past and has been available in beta beta beta for beta beta .,