File size: 1,624 Bytes
e23629c fb2a60d e23629c fb2a60d e23629c fb2a60d e23629c fb2a60d |
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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
{
"added_tokens_decoder": {
"256": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"257": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"258": {
"content": "[BOW]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"259": {
"content": "[EOW]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"260": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[BOW]",
"[EOW]"
],
"clean_up_tokenization_spaces": true,
"do_basic_tokenize": true,
"do_lower_case": true,
"cls_token": "[CLS]",
"sep_token": "[SEP]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"max_word_length": 50,
"model_max_length": 512,
"never_split": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "CharacterBertTokenizer"
}
|