upload files
Browse files- merges.txt +0 -0
- model.safetensors.index.json +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- vocab.json +0 -0
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
|
30 |
+
"bos_token": null,
|
31 |
+
"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 %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "<|im_end|>",
|
34 |
+
"errors": "replace",
|
35 |
+
"model_max_length": 131072,
|
36 |
+
"pad_token": "<|endoftext|>",
|
37 |
+
"split_special_tokens": false,
|
38 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
39 |
+
"unk_token": null
|
40 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|