MiniChat-3B / tokenizer_config.json
GeneZC's picture
Update tokenizer_config.json
5b91092 verified
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{{ '‘MiniChat’是一个由‘Beccurio’开发的AI语言模型。下面是人类和MiniChat之间的一段对话。MiniChat的回复应当尽可能详细,并且以Markdown的形式输出。MiniChat应当拒绝参与违背伦理的讨论。</s>' }}{% for message in messages %}{{'[|' + message['role'].capitalize() + '|] ' + message['content'] + '</s>'}}{% endfor %}{{ '[|Assistant|]' }}",
"use_fast": true
}