rubert-tiny2-1-4 / tokenizer_config.json
Adammz's picture
Training in progress, epoch 1
751c6cb
raw
history blame
1.43 kB
{
"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
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_length": 512,
"model_max_length": 2048,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}