|
{ |
|
"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 |
|
}, |
|
"64000": { |
|
"content": "<mask>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"64001": { |
|
"content": "<s_extraction>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"64002": { |
|
"content": "</s_extraction>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"64003": { |
|
"content": "<s_document_type>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"64004": { |
|
"content": "</s_document_type>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"64005": { |
|
"content": "<s_pair_ocr>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
} |
|
}, |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": false, |
|
"cls_token": "<s>", |
|
"eos_token": "</s>", |
|
"mask_token": "<mask>", |
|
"model_max_length": 1000000000000000019884624838656, |
|
"pad_token": "<pad>", |
|
"processor_class": "DonutProcessor", |
|
"sep_token": "</s>", |
|
"tokenizer_class": "PhobertTokenizer", |
|
"unk_token": "<unk>" |
|
} |
|
|