TelephonePhising / tokenizer /tokenizer_config.json
Rqwannn's picture
Upload tokenizer
20abce3 verified
{
"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": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30521": {
"content": "[SPEAKER_00]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30522": {
"content": "[SPEAKER_01]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30523": {
"content": "[SPEAKER_02]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30524": {
"content": "[SPEAKER_03]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30525": {
"content": "[SPEAKER_04]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30526": {
"content": "[SPEAKER_05]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30527": {
"content": "[CHUNK_START]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30528": {
"content": "[CHUNK_END]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30529": {
"content": "[CHUNK_CONTINUATION]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}