|
{ |
|
"add_bos_token": false, |
|
"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 |
|
}, |
|
"3": { |
|
"content": "<pad>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"4": { |
|
"content": "<cls>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"5": { |
|
"content": "<sep>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"6": { |
|
"content": "<mask>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"additional_special_tokens": [ |
|
"<unk>", |
|
"<s>", |
|
"</s>", |
|
"<pad>", |
|
"<cls>", |
|
"<sep>", |
|
"<mask>" |
|
], |
|
"auto_map": { |
|
"AutoTokenizer": [ |
|
"tokenization_plamo.PlamoTokenizer", |
|
null |
|
] |
|
}, |
|
"bos_token": "<s>", |
|
"chat_template": "{{ '以下はタスクを説明する指示で、文脈を説明した入力とペアになっています。要求を適切に補完するよう応答を書いてください。\n\n' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '### 指示:\n' + message['content'].strip() + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### 入力:\n' + message['content'].strip() + '\n\n' }}{% endif %}{% endfor %}{{ '### 応答:' }}", |
|
"clean_up_tokenization_spaces": false, |
|
"cls_token": "<cls>", |
|
"eos_token": "</s>", |
|
"local_file_only": true, |
|
"mask_token": "<mask>", |
|
"model_max_length": 8192, |
|
"pad_token": "<pad>", |
|
"sep_token": "<sep>", |
|
"sp_model_kwargs": {}, |
|
"tokenizer_class": "PlamoTokenizer", |
|
"tokenizer_file": null, |
|
"unk_token": "<unk>" |
|
} |