File size: 3,249 Bytes
5d1d4ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
{
  "add_prefix_space": 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
    },
    "96499": {
      "content": "<|start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96500": {
      "content": "<|end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96501": {
      "content": "<|message|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96502": {
      "content": "<|tool_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96503": {
      "content": "<|tool_excute|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96504": {
      "content": "<|tool_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96505": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96506": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|start|>",
    "<|end|>",
    "<|message|>",
    "<|tool_start|>",
    "<|tool_excute|>",
    "<|tool_end|>",
    "<|pad|>",
    "<|endoftext|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_inflm.INFLMTokenizer",
      null
    ]
  },
  "bos_token": "<s>",
  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{% if not loop.first %}{{ '\\n' }}{% endif %}{{'<|start|>user\\n' + message['content'] + '<|end|>\\n' }}{% if (loop.last and add_generation_prompt) %}{{ '<|start|>assistant<|message|>' }}{% endif %}{% elif message['role'] == 'system' %}{{ '<|start|>system\\n' + message['content'] + '<|end|>' }}{% elif message['role'] == 'assistant' %}{{ '<|start|>assistant<|message|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "return_tensors": true,
  "spaces_between_special_tokens": false,
  "tokenizer_class": "INFLMTokenizer",
  "unk_token": "<unk>"
}