|
{ |
|
"add_bos_token": true, |
|
"add_eos_token": false, |
|
"added_tokens_decoder": { |
|
"0": { |
|
"content": "<unk>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"1": { |
|
"content": "<s>", |
|
"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 |
|
}, |
|
"32007": { |
|
"content": "<PRE>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"32008": { |
|
"content": "<SUF>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"32009": { |
|
"content": "<MID>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"32010": { |
|
"content": "<EOT>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"32016": { |
|
"content": "<START>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"32017": { |
|
"content": "<END>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"additional_special_tokens": [ |
|
"<PRE>", |
|
"<MID>", |
|
"<SUF>", |
|
"<EOT>", |
|
"<START>", |
|
"<END>" |
|
], |
|
"auto_map": { |
|
"AutoTokenizer": [ |
|
"tokenization_llama.FixLlamaTokenizer", |
|
"tokenization_llama.FixLlamaTokenizerFast" |
|
] |
|
}, |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "</s>", |
|
"legacy": false, |
|
"model_max_length": 1000000000000000019884624838656, |
|
"pad_token": null, |
|
"sp_model_kwargs": {}, |
|
"spaces_between_special_tokens": false, |
|
"tokenizer_class": "FixLlamaTokenizer", |
|
"unk_token": "<unk>", |
|
"use_default_system_prompt": false |
|
} |
|
|