distilbert-base-multilingual-cased-hyper-matt
/
run-7naa0m57
/checkpoint-1200
/tokenizer_config.json
{ | |
"added_tokens_decoder": { | |
"0": { | |
"content": "[PAD]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"100": { | |
"content": "[UNK]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"101": { | |
"content": "[CLS]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"102": { | |
"content": "[SEP]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"103": { | |
"content": "[MASK]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
} | |
}, | |
"clean_up_tokenization_spaces": false, | |
"cls_token": "[CLS]", | |
"do_lower_case": false, | |
"mask_token": "[MASK]", | |
"model_max_length": 512, | |
"pad_token": "[PAD]", | |
"sep_token": "[SEP]", | |
"strip_accents": null, | |
"tokenize_chinese_chars": true, | |
"tokenizer_class": "DistilBertTokenizer", | |
"unk_token": "[UNK]" | |
} | |