neobert-tokenizer-test / special_tokens_map.json
lgienapp's picture
Upload tokenizer
9226f72 verified
{
"additional_special_tokens": [
"[UNK]",
"[SEP]",
"[PAD]",
"[CLS]",
"[MASK]",
"[EOS]",
"[UNSD_TOK_1]",
"[UNSD_TOK_2]",
"[UNSD_TOK_3]",
"[UNSD_TOK_4]",
"[UNSD_TOK_5]",
"[UNSD_TOK_6]",
"[UNSD_TOK_7]",
"[UNSD_TOK_8]",
"[UNSD_TOK_9]",
"[UNSD_TOK_10]",
"[UNSD_TOK_11]",
"[UNSD_TOK_12]",
"[UNSD_TOK_13]",
"[UNSD_TOK_14]",
"[UNSD_TOK_15]",
"[UNSD_TOK_16]",
"[UNSD_TOK_17]",
"[UNSD_TOK_18]",
"[UNSD_TOK_19]",
"[UNSD_TOK_20]",
"[UNSD_TOK_21]",
"[UNSD_TOK_22]",
"[UNSD_TOK_23]",
"[UNSD_TOK_24]",
"[UNSD_TOK_25]",
"[UNSD_TOK_26]",
"[UNSD_TOK_27]",
"[UNSD_TOK_28]",
"[UNSD_TOK_29]",
"[UNSD_TOK_30]",
"[UNSD_TOK_31]",
"[UNSD_TOK_32]",
"[UNSD_TOK_33]",
"[UNSD_TOK_34]",
"[UNSD_TOK_35]",
"[UNSD_TOK_36]",
"[UNSD_TOK_37]",
"[UNSD_TOK_38]",
"[UNSD_TOK_39]",
"[UNSD_TOK_40]",
"[UNSD_TOK_41]",
"[UNSD_TOK_42]",
"[UNSD_TOK_43]",
"[UNSD_TOK_44]",
"[UNSD_TOK_45]",
"[UNSD_TOK_46]",
"[UNSD_TOK_47]",
"[UNSD_TOK_48]",
"[UNSD_TOK_49]",
"[UNSD_TOK_50]",
"[UNSD_TOK_51]",
"[UNSD_TOK_52]",
"[UNSD_TOK_53]",
"[UNSD_TOK_54]",
"[UNSD_TOK_55]",
"[UNSD_TOK_56]",
"[UNSD_TOK_57]",
"[UNSD_TOK_58]",
"[UNSD_TOK_59]",
"[UNSD_TOK_60]",
"[UNSD_TOK_61]",
"[UNSD_TOK_62]",
"[UNSD_TOK_63]",
"[UNSD_TOK_64]",
"[UNSD_TOK_65]",
"[UNSD_TOK_66]",
"[UNSD_TOK_67]",
"[UNSD_TOK_68]",
"[UNSD_TOK_69]",
"[UNSD_TOK_70]",
"[UNSD_TOK_71]",
"[UNSD_TOK_72]",
"[UNSD_TOK_73]",
"[UNSD_TOK_74]",
"[UNSD_TOK_75]",
"[UNSD_TOK_76]",
"[UNSD_TOK_77]",
"[UNSD_TOK_78]",
"[UNSD_TOK_79]",
"[UNSD_TOK_80]",
"[UNSD_TOK_81]",
"[UNSD_TOK_82]",
"[UNSD_TOK_83]",
"[UNSD_TOK_84]",
"[UNSD_TOK_85]",
"[UNSD_TOK_86]",
"[UNSD_TOK_87]",
"[UNSD_TOK_88]",
"[UNSD_TOK_89]",
"[UNSD_TOK_90]",
"[UNSD_TOK_91]",
"[UNSD_TOK_92]",
"[UNSD_TOK_93]",
"[UNSD_TOK_94]",
"[UNSD_TOK_95]",
"[UNSD_TOK_96]",
"[UNSD_TOK_97]",
"[UNSD_TOK_98]",
"[UNSD_TOK_99]",
"[UNSD_TOK_100]",
"[UNSD_TOK_101]",
"[UNSD_TOK_102]",
"[UNSD_TOK_103]",
"[UNSD_TOK_104]",
"[UNSD_TOK_105]",
"[UNSD_TOK_106]",
"[UNSD_TOK_107]",
"[UNSD_TOK_108]",
"[UNSD_TOK_109]",
"[UNSD_TOK_110]",
"[UNSD_TOK_111]",
"[UNSD_TOK_112]",
"[UNSD_TOK_113]",
"[UNSD_TOK_114]",
"[UNSD_TOK_115]",
"[UNSD_TOK_116]",
"[UNSD_TOK_117]",
"[UNSD_TOK_118]",
"[UNSD_TOK_119]",
"[UNSD_TOK_120]",
"[UNSD_TOK_121]",
"[UNSD_TOK_122]"
],
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}