csabakecskemeti commited on
Commit
9443087
·
verified ·
1 Parent(s): 31e42b6

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +165 -0
tokenizer_config.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "163584": {
4
+ "content": "[BOS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "163585": {
12
+ "content": "[EOS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "163586": {
20
+ "content": "<|im_end|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "163587": {
28
+ "content": "<|im_user|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "163588": {
36
+ "content": "<|im_assistant|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "163590": {
44
+ "content": "<|start_header_id|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "163591": {
52
+ "content": "<|end_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "163593": {
60
+ "content": "[EOT]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "163594": {
68
+ "content": "<|im_system|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "163595": {
76
+ "content": "<|tool_calls_section_begin|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "163596": {
84
+ "content": "<|tool_calls_section_end|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "163597": {
92
+ "content": "<|tool_call_begin|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "163598": {
100
+ "content": "<|tool_call_argument_begin|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "163599": {
108
+ "content": "<|tool_call_end|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "163601": {
116
+ "content": "<|im_middle|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "163838": {
124
+ "content": "[UNK]",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "163839": {
132
+ "content": "[PAD]",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ }
139
+ },
140
+ "additional_special_tokens": [
141
+ "<|im_end|>",
142
+ "<|im_user|>",
143
+ "<|im_assistant|>",
144
+ "<|start_header_id|>",
145
+ "<|end_header_id|>",
146
+ "[EOT]",
147
+ "<|im_system|>",
148
+ "<|im_middle|>"
149
+ ],
150
+ "bos_token": "[BOS]",
151
+ "clean_up_tokenization_spaces": false,
152
+ "eos_token": "[EOS]",
153
+ "extra_special_tokens": {},
154
+ "chat_template": "{%- if tools -%}\n <|im_system|>tool_declare<|im_middle|>{{ tools | tojson }}<|im_end|>\n{%- endif -%}\n{%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n <|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>\n {%- endif -%}\n {%- if message['role'] == 'system' -%}\n <|im_system|>system<|im_middle|>\n {%- elif message['role'] == 'user' -%}\n <|im_user|>user<|im_middle|>\n {%- elif message['role'] == 'assistant' -%}\n <|im_assistant|>assistant<|im_middle|>\n {%- elif message['role'] == 'tool' -%}\n <|im_system|>tool<|im_middle|>\n {%- endif -%}\n {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}\n {%- if message['content'] -%}{{ message['content'] }}{%- endif -%}\n <|tool_calls_section_begin|>\n {%- for tool_call in message['tool_calls'] -%}\n {%- set func_name = tool_call['function']['name'] -%}\n {%- set formatted_id = 'functions.' + func_name + ':' + loop.index0|string -%}\n <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{{ tool_call['function']['arguments'] | tojson}}<|tool_call_end|>\n {%- endfor -%}\n <|tool_calls_section_end|>\n {%- elif message['role'] == 'tool' -%}\n ## Return of {{ message.tool_call_id }}\\n{{ message['content'] }}\n {%- elif message['content'] is string -%}\n {{ message['content'] }}\n {%- elif message['content'] is not none -%}\n {% for content in message['content'] -%}\n {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n <|media_start|>image<|media_content|><|media_pad|><|media_end|>\n {% else -%}\n {{ content['text'] }}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n <|im_end|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|im_assistant|>assistant<|im_middle|>\n{%- endif -%}",
155
+ "model_max_length": 1000000000000000019884624838656,
156
+ "pad_token": "[PAD]",
157
+ "tokenizer_class": "TikTokenTokenizer",
158
+ "unk_token": "[UNK]",
159
+ "auto_map": {
160
+ "AutoTokenizer": [
161
+ "tokenization_kimi.TikTokenTokenizer",
162
+ null
163
+ ]
164
+ }
165
+ }