mrebel-large-trim-zh / tokenizer_config.json
DarrenChensformer's picture
New model version
90d7728
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"59999": {
"content": "ar_AR",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60000": {
"content": "cs_CZ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60001": {
"content": "de_DE",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60002": {
"content": "en_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60003": {
"content": "es_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60004": {
"content": "et_EE",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60005": {
"content": "fi_FI",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60006": {
"content": "fr_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60007": {
"content": "gu_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60008": {
"content": "hi_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60009": {
"content": "it_IT",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60010": {
"content": "ja_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60011": {
"content": "kk_KZ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60012": {
"content": "ko_KR",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60013": {
"content": "lt_LT",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60014": {
"content": "lv_LV",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60015": {
"content": "my_MM",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60016": {
"content": "ne_NP",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60017": {
"content": "nl_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60018": {
"content": "ro_RO",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60019": {
"content": "ru_RU",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60020": {
"content": "si_LK",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60021": {
"content": "tr_TR",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60022": {
"content": "vi_VN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60023": {
"content": "zh_CN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60024": {
"content": "af_ZA",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60025": {
"content": "az_AZ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60026": {
"content": "bn_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60027": {
"content": "fa_IR",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60028": {
"content": "he_IL",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60029": {
"content": "hr_HR",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60030": {
"content": "id_ID",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60031": {
"content": "ka_GE",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60032": {
"content": "km_KH",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60033": {
"content": "mk_MK",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60034": {
"content": "ml_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60035": {
"content": "mn_MN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60036": {
"content": "mr_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60037": {
"content": "pl_PL",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60038": {
"content": "ps_AF",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60039": {
"content": "pt_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60040": {
"content": "sv_SE",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60041": {
"content": "sw_KE",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60042": {
"content": "ta_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60043": {
"content": "te_IN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60044": {
"content": "th_TH",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60045": {
"content": "tl_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60046": {
"content": "uk_UA",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60047": {
"content": "ur_PK",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60048": {
"content": "xh_ZA",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60049": {
"content": "gl_ES",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60050": {
"content": "sl_SI",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60051": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60052": {
"content": "<triplet>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60053": {
"content": "<relation>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60054": {
"content": "el_EL",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60055": {
"content": "ca_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60056": {
"content": "tp_XX",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60057": {
"content": "<loc>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60058": {
"content": "<misc>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60059": {
"content": "<per>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60060": {
"content": "<num>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60061": {
"content": "<time>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60062": {
"content": "<org>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60063": {
"content": "<date>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60064": {
"content": "<eve>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60065": {
"content": "<cel>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60066": {
"content": "<media>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60067": {
"content": "<dis>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60068": {
"content": "<concept>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<triplet>",
"<relation>",
"el_EL",
"ca_XX",
"tp_XX",
"<loc>",
"<misc>",
"<per>",
"<num>",
"<time>",
"<org>",
"<date>",
"<eve>",
"<cel>",
"<media>",
"<dis>",
"<unk>",
"<concept>",
"ar_AR",
"cs_CZ",
"de_DE",
"en_XX",
"es_XX",
"et_EE",
"fi_FI",
"fr_XX",
"gu_IN",
"hi_IN",
"it_IT",
"ja_XX",
"kk_KZ",
"ko_KR",
"lt_LT",
"lv_LV",
"my_MM",
"ne_NP",
"nl_XX",
"ro_RO",
"ru_RU",
"si_LK",
"tr_TR",
"vi_VN",
"zh_CN",
"af_ZA",
"az_AZ",
"bn_IN",
"fa_IR",
"he_IL",
"hr_HR",
"id_ID",
"ka_GE",
"km_KH",
"mk_MK",
"ml_IN",
"mn_MN",
"mr_IN",
"pl_PL",
"ps_AF",
"pt_XX",
"sv_SE",
"sw_KE",
"ta_IN",
"te_IN",
"th_TH",
"tl_XX",
"uk_UA",
"ur_PK",
"xh_ZA",
"gl_ES",
"sl_SI"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 1024,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"src_lang": "en_XX",
"tgt_lang": "tp_XX",
"tokenizer_class": "MBart50Tokenizer",
"unk_token": "<unk>",
"use_fast": true
}