File size: 1,445 Bytes
9388b3e 60e64cf 9388b3e 60e64cf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
"tokenizer_class": "BertTokenizer",
"special_tokens": {
"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_len": 512,
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenize_chinese_chars": True,
"unk_token": "[UNK]"
}
|