Modelpublic

NikolayRainWay/multitask-toxic-encoder

sourceHugging Facemitupdated 3mo agoView on Hugging Face

0likes4downloads

tokenizer_config.json25 linesDownload Raw Back to root

1{2  "backend": "tokenizers",3  "cls_token": "[CLS]",4  "do_basic_tokenize": true,5  "do_lower_case": false,6  "is_local": false,7  "local_files_only": false,8  "mask_token": "[MASK]",9  "max_length": 512,10  "model_max_length": 2048,11  "never_split": null,12  "pad_to_multiple_of": null,13  "pad_token": "[PAD]",14  "pad_token_type_id": 0,15  "padding_side": "right",16  "sep_token": "[SEP]",17  "stride": 0,18  "strip_accents": null,19  "tokenize_chinese_chars": true,20  "tokenizer_class": "BertTokenizer",21  "truncation_side": "right",22  "truncation_strategy": "longest_first",23  "unk_token": "[UNK]"24}25