Bert Kor Base

🚀 Bert base model for Korean

This project offers a BERT base model for Korean, trained on a 70GB Korean text dataset with 42000 lower - cased subwords. You can check the model performance and compare it with other Korean language models on github.

🚀 Quick Start

This BERT base model for Korean is trained using a 70GB Korean text dataset and 42000 lower - cased subwords. You can check the model performance and other Korean language models on github.

💻 Usage Examples

Basic Usage

from transformers import BertTokenizerFast, BertModel

tokenizer_bert = BertTokenizerFast.from_pretrained("kykim/bert-kor-base")
model_bert = BertModel.from_pretrained("kykim/bert-kor-base")