|
{ |
|
"_commit_hash": "975930d21cd02e484509b28286f98a3bf0d2b633", |
|
"_from_auto": true, |
|
"added_tokens_decoder": { |
|
"0": { |
|
"content": "[UNK]", |
|
"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": "[BOS]", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"3": { |
|
"content": "[EOS]", |
|
"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 |
|
} |
|
}, |
|
"auto_map": { |
|
"AutoTokenizer": [ |
|
"tokenizer_script.CharacterTokenizer", |
|
null |
|
] |
|
}, |
|
"bos_token": "[BOS]", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "[EOS]", |
|
"extra_special_tokens": {}, |
|
"model_max_length": 1000000000000000019884624838656, |
|
"pad_token": "[PAD]", |
|
"sep_token": "[SEP]", |
|
"tokenizer_class": "CharacterTokenizer", |
|
"trust_remote_code": true, |
|
"unk_token": "[UNK]" |
|
} |
|
|