hate-multi-roberta-hasoc-hindi / tokenizer_config.json

Adding tokenizer config file for multi-class hate speech detection model trained on HASOC Hindi dataset

1d26e2d over 2 years ago

No virus

318 Bytes

{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "flax-community/roberta-hindi", "tokenizer_class": "RobertaTokenizer"}