bert-base-uncased-dstc9 / tokenizer_config.json
wilsontam's picture
MLM trained with DSTC9 train+val set
b144a0c
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "use_fast": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./bert-base-uncased-local", "tokenizer_class": "BertTokenizer"}