|
{ |
|
"add_bos_token": true, |
|
"add_eos_token": false, |
|
"added_tokens_decoder": { |
|
"0": { |
|
"content": "<unk>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"1": { |
|
"content": "<s>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"2": { |
|
"content": "</s>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"32000": { |
|
"content": "<T1>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32001": { |
|
"content": "</T1>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32002": { |
|
"content": "<T2>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32003": { |
|
"content": "</T2>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32004": { |
|
"content": "<T3>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32005": { |
|
"content": "</T3>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32006": { |
|
"content": "<T4>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32007": { |
|
"content": "</T4>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32008": { |
|
"content": "<T5>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32009": { |
|
"content": "</T5>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32010": { |
|
"content": "<T>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32011": { |
|
"content": "</T>", |
|
"lstrip": true, |
|
"normalized": true, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
} |
|
}, |
|
"additional_special_tokens": [], |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "</s>", |
|
"legacy": true, |
|
"model_max_length": 2048, |
|
"pad_token": "<unk>", |
|
"padding_side": "right", |
|
"sp_model_kwargs": {}, |
|
"spaces_between_special_tokens": false, |
|
"tokenizer_class": "LlamaTokenizer", |
|
"tokenizer_file": null, |
|
"unk_token": "<unk>", |
|
"use_default_system_prompt": true |
|
} |
|
|