|
{ |
|
"added_tokens_decoder": { |
|
"0": { |
|
"content": "<pad>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"1": { |
|
"content": "<unk>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"2": { |
|
"content": "<cls>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"3": { |
|
"content": "<sep>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"4": { |
|
"content": "<mask>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"auto_map": { |
|
"AutoTokenizer": [ |
|
"tokenization_liberta.LibertaTokenizer", |
|
null |
|
] |
|
}, |
|
"bos_token": "<cls>", |
|
"clean_up_tokenization_spaces": true, |
|
"cls_token": "<cls>", |
|
"eos_token": "<sep>", |
|
"mask_token": "<mask>", |
|
"model_max_length": 1000000000000000019884624838656, |
|
"pad_token": "<pad>", |
|
"sep_token": "<sep>", |
|
"sp_model_kwargs": {}, |
|
"tokenizer_class": "LibertaTokenizer", |
|
"unk_token": "<unk>" |
|
} |
|
|