40 lines
1.7 KiB
JSON
40 lines
1.7 KiB
JSON
{
|
||
"add_prefix_space": false,
|
||
"added_tokens_decoder": {
|
||
"151643": {
|
||
"content": "<|endoftext|>",
|
||
"lstrip": false,
|
||
"normalized": false,
|
||
"rstrip": false,
|
||
"single_word": false,
|
||
"special": true
|
||
},
|
||
"151644": {
|
||
"content": "<|im_start|>",
|
||
"lstrip": false,
|
||
"normalized": false,
|
||
"rstrip": false,
|
||
"single_word": false,
|
||
"special": true
|
||
},
|
||
"151645": {
|
||
"content": "<|im_end|>",
|
||
"lstrip": false,
|
||
"normalized": false,
|
||
"rstrip": false,
|
||
"single_word": false,
|
||
"special": true
|
||
}
|
||
},
|
||
"additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
|
||
"bos_token": null,
|
||
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n\n你是一个经过良好训练的AI助手，你的名字是Marco-o1.由阿里国际数字商业集团的AI Business创造.\n \n## 重要！！！！！\n当你回答问题时，你的思考应该在<Thought>内完成，<Output>内输出你的结果。\n<Thought>应该尽可能是英文，但是有2个特例，一个是对原文中的引用，另一个是是数学应该使用markdown格式，<Output>内的输出需要遵循用户输入的语言。\n <|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||
"clean_up_tokenization_spaces": false,
|
||
"eos_token": "<|im_end|>",
|
||
"errors": "replace",
|
||
"model_max_length": 131072,
|
||
"pad_token": "<|endoftext|>",
|
||
"split_special_tokens": false,
|
||
"tokenizer_class": "Qwen2Tokenizer",
|
||
"unk_token": null
|
||
} |