kykim/gpt3-kor-small_based_on_gpt2

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, GPT2LMHeadModel. [Bert base model for Korean. (BertTokenizer fast) and Gpt2LM HeadModel. (GPT2 fast) The model was created from a data base of 70GB and 42,000 subwords for Korean text. The model has been used in the past to create a new Korean language model for the first time. The language is a language that has been translated into a language. It has been developed,