ryo0634's picture
Upload tokenizer
68dbf4d verified
raw
history blame
1.4 kB
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"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
}
},
"bos_token": "<s>",
"chat_template": "{%- for message in messages %}\n{%- if message['role'] == 'user' %}\n{{ bos_token + 'ユーザ:' + message['content'] + eos_token }}\n{%- elif message['role'] == 'assistant' %}\n{{ bos_token + 'アシスタント:' + message['content'] + eos_token }}\n{%- endif %}\n{% if loop.last and add_generation_prompt %}\n{{ bos_token + 'アシスタント:' }}\n{%- endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}