|
{ |
|
"add_bos_token": false, |
|
"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 |
|
} |
|
}, |
|
"auto_map": { |
|
"AutoTokenizer": [ |
|
"tokenization_baichuan.BaichuanTokenizer", |
|
null |
|
] |
|
}, |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "</s>", |
|
"model_max_length": 4096, |
|
"pad_token": "<unk>", |
|
"padding_side": "right", |
|
"sp_model_kwargs": {}, |
|
"split_special_tokens": false, |
|
"tokenizer_class": "BaichuanTokenizer", |
|
"unk_token": "<unk>", |
|
"use_fast": false |
|
} |
|
|