punctuation_fa_parsbert / tokenizer_config.json
AliHF2020's picture
Upload tokenizer
c4ab01c
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"stride": 0,
"strip_accent": false,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}