Add converted tokenizer (no trust_remote_code needed)

#3
by ArthurZ HF Staff - opened
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +37 -0
  3. tokenizer.json +3 -0
  4. tokenizer_config.json +10 -158
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
  banner.png filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
  banner.png filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if tools -%}
2
+ {{ '<|im_system|>tool_declare<|im_middle|>' -}}
3
+ {{- tools | tojson -}}
4
+ {{ '<|im_end|>' -}}
5
+ {%- endif -%}
6
+
7
+ {%- for message in messages -%}
8
+ {%- if loop.first and messages[0]['role'] != 'system' -%}
9
+ {{ '<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>' }}
10
+ {%- endif -%}
11
+ {%- if message['role'] == 'system' -%}
12
+ {{ '<|im_system|>system<|im_middle|>' }}
13
+ {%- elif message['role'] == 'user' -%}
14
+ {{ '<|im_user|>user<|im_middle|>' }}
15
+ {%- elif message['role'] == 'assistant' -%}
16
+ {{ '<|im_assistant|>assistant<|im_middle|>' }}
17
+ {%- elif message['role'] == 'tool' -%}
18
+ {{ '<|im_system|>tool<|im_middle|>' }}
19
+ {%- endif -%}
20
+
21
+ {%- if message['content'] is string -%}
22
+ {{- message['content'] + '<|im_end|>' -}}
23
+ {%- else -%}
24
+ {%- for content in message['content'] -%}
25
+ {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
26
+ {{ '<|media_start|>image<|media_content|><|media_pad|><|media_end|>' }}
27
+ {%- else -%}
28
+ {{ content['text'] }}
29
+ {%- endif -%}
30
+ {%- endfor -%}
31
+ {{ '<|im_end|>' }}
32
+ {%- endif -%}
33
+ {%- endfor -%}
34
+
35
+ {%- if add_generation_prompt -%}
36
+ {{ '<|im_assistant|>assistant<|im_middle|>' }}
37
+ {%- endif -%}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ec426a05b6cfb107053944445ca6ca642fef207704fe4d5112053b17803334
3
+ size 19544371
tokenizer_config.json CHANGED
@@ -1,165 +1,17 @@
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|>' -}}\n {{- tools | tojson -}}\n {{ '<|im_end|>' -}}\n{%- endif -%}\n\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\n {%- if message['content'] is string -%}\n {{- message['content'] + '<|im_end|>' -}}\n {%- else -%}\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 {{ '<|im_end|>' }}\n {%- endif -%}\n{%- endfor -%}\n\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
- }
 
1
  {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_kimi.TikTokenTokenizer",
5
+ null
6
+ ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  },
8
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
9
  "bos_token": "[BOS]",
10
  "clean_up_tokenization_spaces": false,
11
  "eos_token": "[EOS]",
12
+ "is_local": false,
 
13
  "model_max_length": 1000000000000000019884624838656,
14
  "pad_token": "[PAD]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }