urdu-codemixed-abusive-MuRIL / tokenizer_config.json
leowin's picture
Upload tokenizer_config.json
f3a63fc
raw
history blame
522 Bytes
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "lowercase": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/290471f6a01c9af0dd0bcf02112dc77b9b0aee820ebb1fb023c96ac2dda9d8ef.750293617705dd39d21eef1e163d80ca5b23e1a0ec507fff24a087c44632142c", "name_or_path": "UrduCode/", "tokenizer_class": "BertTokenizer"}