maksym-unlp-6 / tokenizer_config.json
lenguist's picture
Training in progress, epoch 1
96d6cbf
{
"additional_special_tokens": [
"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>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1024,
"name_or_path": "facebook/mbart-large-50",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
"src_lang": "uk_UA",
"tgt_lang": "uk_UA",
"tokenizer_class": "MBart50Tokenizer",
"unk_token": "<unk>"
}