kykim/electra-kor-base
The kykim/electra-kor-base model is a machine learning model.
About kykim/electra-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 Electra base model for Korean is based on the ElectraTokenizerFast and ElectraModel.model.from_pretrained("kykim/electra-kor-base") The model was created from a database of 70,000 Korean text files and 42,000 subwords . For more information on the Korean model, visit http://://www.kim.org/korean-model-base-test/korea-test-model.com/test-test.com .,