neobert-tokenizer-test / tokenizer_config.json
lgienapp's picture
Upload tokenizer
9226f72 verified
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[CLS]",
"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
},
"5": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "[UNSD_TOK_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "[UNSD_TOK_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "[UNSD_TOK_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "[UNSD_TOK_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "[UNSD_TOK_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "[UNSD_TOK_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "[UNSD_TOK_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "[UNSD_TOK_8]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "[UNSD_TOK_9]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "[UNSD_TOK_10]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "[UNSD_TOK_11]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "[UNSD_TOK_12]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": "[UNSD_TOK_13]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"19": {
"content": "[UNSD_TOK_14]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20": {
"content": "[UNSD_TOK_15]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21": {
"content": "[UNSD_TOK_16]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"22": {
"content": "[UNSD_TOK_17]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"23": {
"content": "[UNSD_TOK_18]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"24": {
"content": "[UNSD_TOK_19]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"25": {
"content": "[UNSD_TOK_20]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"26": {
"content": "[UNSD_TOK_21]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"27": {
"content": "[UNSD_TOK_22]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"28": {
"content": "[UNSD_TOK_23]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"29": {
"content": "[UNSD_TOK_24]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30": {
"content": "[UNSD_TOK_25]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31": {
"content": "[UNSD_TOK_26]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32": {
"content": "[UNSD_TOK_27]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "[UNSD_TOK_28]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"34": {
"content": "[UNSD_TOK_29]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"35": {
"content": "[UNSD_TOK_30]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36": {
"content": "[UNSD_TOK_31]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"37": {
"content": "[UNSD_TOK_32]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"38": {
"content": "[UNSD_TOK_33]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"39": {
"content": "[UNSD_TOK_34]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"40": {
"content": "[UNSD_TOK_35]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"41": {
"content": "[UNSD_TOK_36]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"42": {
"content": "[UNSD_TOK_37]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"43": {
"content": "[UNSD_TOK_38]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"44": {
"content": "[UNSD_TOK_39]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"45": {
"content": "[UNSD_TOK_40]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"46": {
"content": "[UNSD_TOK_41]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"47": {
"content": "[UNSD_TOK_42]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"48": {
"content": "[UNSD_TOK_43]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49": {
"content": "[UNSD_TOK_44]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50": {
"content": "[UNSD_TOK_45]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"51": {
"content": "[UNSD_TOK_46]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"52": {
"content": "[UNSD_TOK_47]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"53": {
"content": "[UNSD_TOK_48]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"54": {
"content": "[UNSD_TOK_49]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"55": {
"content": "[UNSD_TOK_50]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"56": {
"content": "[UNSD_TOK_51]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"57": {
"content": "[UNSD_TOK_52]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"58": {
"content": "[UNSD_TOK_53]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"59": {
"content": "[UNSD_TOK_54]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60": {
"content": "[UNSD_TOK_55]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61": {
"content": "[UNSD_TOK_56]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"62": {
"content": "[UNSD_TOK_57]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"63": {
"content": "[UNSD_TOK_58]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64": {
"content": "[UNSD_TOK_59]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65": {
"content": "[UNSD_TOK_60]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"66": {
"content": "[UNSD_TOK_61]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"67": {
"content": "[UNSD_TOK_62]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"68": {
"content": "[UNSD_TOK_63]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"69": {
"content": "[UNSD_TOK_64]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"70": {
"content": "[UNSD_TOK_65]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"71": {
"content": "[UNSD_TOK_66]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"72": {
"content": "[UNSD_TOK_67]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73": {
"content": "[UNSD_TOK_68]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"74": {
"content": "[UNSD_TOK_69]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75": {
"content": "[UNSD_TOK_70]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"76": {
"content": "[UNSD_TOK_71]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"77": {
"content": "[UNSD_TOK_72]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"78": {
"content": "[UNSD_TOK_73]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"79": {
"content": "[UNSD_TOK_74]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"80": {
"content": "[UNSD_TOK_75]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"81": {
"content": "[UNSD_TOK_76]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"82": {
"content": "[UNSD_TOK_77]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"83": {
"content": "[UNSD_TOK_78]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"84": {
"content": "[UNSD_TOK_79]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"85": {
"content": "[UNSD_TOK_80]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"86": {
"content": "[UNSD_TOK_81]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"87": {
"content": "[UNSD_TOK_82]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"88": {
"content": "[UNSD_TOK_83]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"89": {
"content": "[UNSD_TOK_84]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"90": {
"content": "[UNSD_TOK_85]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"91": {
"content": "[UNSD_TOK_86]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92": {
"content": "[UNSD_TOK_87]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"93": {
"content": "[UNSD_TOK_88]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"94": {
"content": "[UNSD_TOK_89]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"95": {
"content": "[UNSD_TOK_90]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96": {
"content": "[UNSD_TOK_91]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"97": {
"content": "[UNSD_TOK_92]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"98": {
"content": "[UNSD_TOK_93]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"99": {
"content": "[UNSD_TOK_94]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNSD_TOK_95]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[UNSD_TOK_96]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[UNSD_TOK_97]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[UNSD_TOK_98]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"104": {
"content": "[UNSD_TOK_99]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"105": {
"content": "[UNSD_TOK_100]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "[UNSD_TOK_101]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"107": {
"content": "[UNSD_TOK_102]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"108": {
"content": "[UNSD_TOK_103]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"109": {
"content": "[UNSD_TOK_104]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110": {
"content": "[UNSD_TOK_105]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"111": {
"content": "[UNSD_TOK_106]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"112": {
"content": "[UNSD_TOK_107]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"113": {
"content": "[UNSD_TOK_108]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"114": {
"content": "[UNSD_TOK_109]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"115": {
"content": "[UNSD_TOK_110]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"116": {
"content": "[UNSD_TOK_111]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"117": {
"content": "[UNSD_TOK_112]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"118": {
"content": "[UNSD_TOK_113]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"119": {
"content": "[UNSD_TOK_114]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"120": {
"content": "[UNSD_TOK_115]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"121": {
"content": "[UNSD_TOK_116]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"122": {
"content": "[UNSD_TOK_117]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"123": {
"content": "[UNSD_TOK_118]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"124": {
"content": "[UNSD_TOK_119]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"125": {
"content": "[UNSD_TOK_120]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"126": {
"content": "[UNSD_TOK_121]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"127": {
"content": "[UNSD_TOK_122]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"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]"
],
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"eos_token": "[EOS]",
"extra_special_tokens": {},
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]",
"vocab_size": 49152
}