|
{ |
|
"add_prefix_space": true, |
|
"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 |
|
}, |
|
"250001": { |
|
"content": "<mask>", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": true, |
|
"cls_token": "<s>", |
|
"eos_token": "</s>", |
|
"mask_token": "<mask>", |
|
"max_length": 512, |
|
"model_max_length": 512, |
|
"pad_token": "<pad>", |
|
"sep_token": "</s>", |
|
"stride": 0, |
|
"strip_accent": false, |
|
"tokenizer_class": "XLMRobertaTokenizer", |
|
"truncation_side": "right", |
|
"truncation_strategy": "longest_first", |
|
"unk_token": "<unk>" |
|
} |
|
|