Pretrained K-mHas with binary-label model with "koelectra-v3"
You can use tokenizer of this model with "monologg/koelectra-v3-base-discriminator"
dataset : https://huggingface.co/datasets/jeanlee/kmhas_korean_hate_speech
pretrained_model : https://huggingface.co/monologg/koelectra-base-v3-discriminator
label maps are like this.
{0: "not_hate_speech", 1: "hate_speech"}