ro-tokenizer / tokenizer_config.json
alina0195's picture
init
cd9e7ed verified
{
"added_tokens_decoder": {
"0": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"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": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"19": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"22": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"23": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"24": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"25": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"26": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"27": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"model_max_length": 128000,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}