wirehead82 commited on
Commit
fd1b1fa
·
verified ·
1 Parent(s): a9a82f5

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,4 +1,3 @@
1
  {
2
- "<end_of_image>": 262145,
3
  "<image_soft_token>": 262144
4
  }
 
1
  {
 
2
  "<image_soft_token>": 262144
3
  }
chat_template.jinja CHANGED
@@ -1,279 +1,47 @@
1
- {%- macro format_parameters(properties, required) -%}
2
- {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
3
- {%- set ns = namespace(found_first=false) -%}
4
- {%- for key, value in properties | dictsort -%}
5
- {%- if key not in standard_keys -%}
6
- {%- if ns.found_first %},{% endif -%}
7
- {%- set ns.found_first = true -%}
8
- {{- key }}:{description:<escape>{{ value['description'] }}<escape>
9
- {%- if value['type'] | upper == 'STRING' -%}
10
- {%- if value['enum'] -%}
11
- ,enum:{{ format_argument(value['enum']) }}
12
- {%- endif -%}
13
- {%- elif value['type'] | upper == 'OBJECT' -%}
14
- ,properties:{
15
- {%- if value['properties'] is defined and value['properties'] is mapping -%}
16
- {{- format_parameters(value['properties'], value['required'] | default([])) -}}
17
- {%- elif value is mapping -%}
18
- {{- format_parameters(value, value['required'] | default([])) -}}
19
- {%- endif -%}
20
- }
21
- {%- if value['required'] -%}
22
- ,required:[
23
- {%- for item in value['required'] | default([]) -%}
24
- <escape>{{- item -}}<escape>
25
- {%- if not loop.last %},{% endif -%}
26
- {%- endfor -%}
27
- ]
28
- {%- endif -%}
29
- {%- elif value['type'] | upper == 'ARRAY' -%}
30
- {%- if value['items'] is mapping and value['items'] -%}
31
- ,items:{
32
- {%- set ns_items = namespace(found_first=false) -%}
33
- {%- for item_key, item_value in value['items'] | dictsort -%}
34
- {%- if item_value is not none -%}
35
- {%- if ns_items.found_first %},{% endif -%}
36
- {%- set ns_items.found_first = true -%}
37
- {%- if item_key == 'properties' -%}
38
- properties:{
39
- {%- if item_value is mapping -%}
40
- {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
41
- {%- endif -%}
42
- }
43
- {%- elif item_key == 'required' -%}
44
- required:[
45
- {%- for req_item in item_value -%}
46
- <escape>{{- req_item -}}<escape>
47
- {%- if not loop.last %},{% endif -%}
48
- {%- endfor -%}
49
- ]
50
- {%- elif item_key == 'type' -%}
51
- {%- if item_value is string -%}
52
- type:{{ format_argument(item_value | upper) }}
53
- {%- else -%}
54
- type:{{ format_argument(item_value | map('upper') | list) }}
55
- {%- endif -%}
56
- {%- else -%}
57
- {{ item_key }}:{{ format_argument(item_value) }}
58
- {%- endif -%}
59
- {%- endif -%}
60
- {%- endfor -%}
61
- }
62
- {%- endif -%}
63
- {%- endif -%}
64
- ,type:<escape>{{ value['type'] | upper }}<escape>}
65
- {%- endif -%}
66
- {%- endfor -%}
67
- {%- endmacro -%}
68
- {% macro format_function_declaration(tool_data) -%}
69
- declaration:{{- tool_data['function']['name'] -}}
70
- {description:<escape>{{- tool_data['function']['description'] -}}<escape>
71
- {%- set params = tool_data['function']['parameters'] -%}
72
- {%- if params -%}
73
- ,parameters:{
74
- {%- if params['properties'] -%}
75
- properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
76
- {%- endif -%}
77
- {%- if params['required'] -%}
78
- required:[
79
- {%- for item in params['required'] -%}
80
- <escape>{{- item -}}<escape>
81
- {{- ',' if not loop.last -}}
82
- {%- endfor -%}
83
- ],
84
- {%- endif -%}
85
- {%- if params['type'] -%}
86
- type:<escape>{{- params['type'] | upper -}}<escape>}
87
- {%- endif -%}
88
- {%- endif -%}
89
- }
90
- {%- endmacro -%}
91
- {% macro format_argument(argument, escape_keys=True) -%}
92
- {%- if argument is string -%}
93
- {{- '<escape>' + argument + '<escape>' -}}
94
- {%- elif argument is boolean -%}
95
- {%- if argument -%}
96
- {{- 'true' -}}
97
  {%- else -%}
98
- {{- 'false' -}}
 
 
99
  {%- endif -%}
100
- {%- elif argument is mapping -%}
101
- {{- '{' -}}
102
- {%- set ns = namespace(found_first=false) -%}
103
- {%- for key, value in argument | dictsort -%}
104
- {%- if ns.found_first %},{% endif -%}
105
- {%- set ns.found_first = true -%}
106
- {%- if escape_keys -%}
107
- {{- '<escape>' + key + '<escape>' -}}
108
- {%- else -%}
109
- {{- key -}}
110
- {%- endif -%}
111
- :{{- format_argument(value, escape_keys=escape_keys) -}}
112
- {%- endfor -%}
113
- {{- '}' -}}
114
- {%- elif argument is sequence -%}
115
- {{- '[' -}}
116
- {%- for item in argument -%}
117
- {{- format_argument(item, escape_keys=escape_keys) -}}
118
- {%- if not loop.last %},{% endif -%}
119
- {%- endfor -%}
120
- {{- ']' -}}
121
  {%- else -%}
122
- {{- argument -}}
 
123
  {%- endif -%}
124
- {%- endmacro -%}
125
- {{ bos_token }}
126
- {%- set ns = namespace(prev_message_type=None) -%}
127
- {#- Tool Declarations -#}
128
- {%- set loop_messages = messages -%}
129
- {%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
130
- {{- '<start_of_turn>developer\n' -}}
131
- {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
132
- {%- if messages[0]['content'] is string -%}
133
- {{- messages[0]['content'] | trim -}}
134
- {%- elif messages[0]['content'] is sequence -%}
135
- {%- for item in messages[0]['content'] -%}
136
- {%- if item['type'] == 'text' -%}
137
- {{- item['text'] | trim -}}
138
- {%- endif -%}
139
- {%- endfor -%}
140
- {%- endif -%}
141
- {%- set loop_messages = messages[1:] -%}
142
- {%- endif -%}
143
- {%- if tools -%}
144
- {%- for tool in tools %}
145
- {{- '<start_function_declaration>' -}}
146
- {{- format_function_declaration(tool) | trim }}
147
- {{- '<end_function_declaration>' -}}
148
- {%- endfor %}
149
- {%- endif -%}
150
- {{- '<end_of_turn>\n' }}
151
- {%- endif %}
152
- {#- Loop through messages. -#}
153
  {%- for message in loop_messages -%}
 
 
 
154
  {%- if (message['role'] == 'assistant') -%}
155
- {#- Rename "assistant" to "model". -#}
156
  {%- set role = "model" -%}
157
  {%- else -%}
158
  {%- set role = message['role'] -%}
159
  {%- endif -%}
160
- {%- if role != 'tool' -%}
161
- {%- if ns.prev_message_type != 'tool_response' -%}
162
- {{- '<start_of_turn>' + role + '\n' }}
163
- {%- endif -%}
164
- {%- set ns.prev_message_type = None -%}
165
- {%- if 'content' in message and message['content'] is not none -%}
166
- {%- if message['content'] is string -%}
167
- {{ message['content'] | trim }}
168
- {%- elif message['content'] is sequence -%}
169
- {%- for item in message['content'] -%}
170
- {%- if item['type'] == 'image' -%}
171
- {{ '<start_of_image>' }}
172
- {%- elif item['type'] == 'text' -%}
173
- {{ item['text'] | trim }}
174
- {%- endif -%}
175
- {%- endfor -%}
176
- {%- else -%}
177
- {{ raise_exception("Invalid content type in user/assistant message") }}
178
- {%- endif -%}
179
- {%- set ns.prev_message_type = 'content' -%}
180
- {%- endif -%}
181
- {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
182
- {#- Tool Calls -#}
183
- {%- for tool_call in message['tool_calls'] -%}
184
- {% set function = tool_call['function'] %}
185
- {{- '<start_function_call>call:' + function['name'] + '{' -}}
186
- {%- if 'arguments' in function -%}
187
- {%- if function['arguments'] is mapping -%}
188
- {%- set ns = namespace(found_first=false) -%}
189
- {%- for key, value in function['arguments'] | dictsort -%}
190
- {%- if ns.found_first %},{% endif -%}
191
- {%- set ns.found_first = true -%}
192
- {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
193
- {%- endfor -%}
194
- {%- elif function['arguments'] is string -%}
195
- {# This handles string-JSON, just in case #}
196
- {{ function['arguments'] }}
197
- {%- endif %}
198
- {%- endif -%}
199
- {{- '}<end_function_call>' -}}
200
- {%- endfor -%}
201
- {%- if loop.last -%}
202
- {{ '<start_function_response>' }}
203
  {%- endif -%}
204
- {%- set ns.prev_message_type = 'tool_call' -%}
205
- {%- endif -%}
206
  {%- else -%}
207
- {#- Tool Responses -#}
208
- {%- if 'content' in message and message['content'] -%}
209
- {%- if message['content'] is mapping -%}
210
- {%- if 'name' in message['content'] and 'response' in message['content'] -%}
211
- {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
212
- {%- set response_ns = namespace(found_first=false) -%}
213
- {%- for key, value in message['content']['response'] | dictsort -%}
214
- {%- if response_ns.found_first %},{% endif -%}
215
- {%- set response_ns.found_first = true -%}
216
- {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
217
- {%- endfor -%}
218
- {{- '}<end_function_response>' -}}
219
- {%- elif 'name' in message -%}
220
- {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
221
- {%- set response_ns = namespace(found_first=false) -%}
222
- {%- for key, value in message['content'] | dictsort -%}
223
- {%- if response_ns.found_first %},{% endif -%}
224
- {%- set response_ns.found_first = true -%}
225
- {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
226
- {%- endfor -%}
227
- {{- '}<end_function_response>' -}}
228
- {%- else -%}
229
- {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
230
- {%- endif -%}
231
- {%- elif message['content'] is string -%}
232
- {%- if 'name' in message -%}
233
- {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
234
- {%- else -%}
235
- {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
236
- {%- endif -%}
237
- {%- elif message['content'] is sequence -%}
238
- {%- for item in message['content'] -%}
239
- {%- if item is mapping -%}
240
- {%- if 'name' in item and 'response' in item -%}
241
- {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
242
- {%- set response_ns = namespace(found_first=false) -%}
243
- {%- for key, value in item['response'] | dictsort -%}
244
- {%- if response_ns.found_first %},{% endif -%}
245
- {%- set response_ns.found_first = true -%}
246
- {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
247
- {%- endfor -%}
248
- {{- '}<end_function_response>' -}}
249
- {%- elif 'name' in message -%}
250
- {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
251
- {%- set response_ns = namespace(found_first=false) -%}
252
- {%- for key, value in item | dictsort -%}
253
- {%- if response_ns.found_first %},{% endif -%}
254
- {%- set response_ns.found_first = true -%}
255
- {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
256
- {%- endfor -%}
257
- {{- '}<end_function_response>' -}}
258
- {%- else -%}
259
- {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
260
- {%- endif -%}
261
- {%- else -%}
262
- {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
263
- {%- endif -%}
264
- {%- endfor -%}
265
- {%- else -%}
266
- {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
267
- {%- endif -%}
268
- {%- endif -%}
269
- {%- set ns.prev_message_type = 'tool_response' -%}
270
- {%- endif -%}
271
- {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
272
- {{ '<end_of_turn>\n' }}
273
  {%- endif -%}
 
 
274
  {%- endfor -%}
275
  {%- if add_generation_prompt -%}
276
- {%- if ns.prev_message_type != 'tool_response' -%}
277
- {{- '<start_of_turn>model\n' -}}
278
- {%- endif -%}
279
  {%- endif -%}
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
  {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
  {%- endif -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
  {%- if (message['role'] == 'assistant') -%}
 
22
  {%- set role = "model" -%}
23
  {%- else -%}
24
  {%- set role = message['role'] -%}
25
  {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  {%- endif -%}
37
+ {%- endfor -%}
 
38
  {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
  {%- endfor -%}
44
  {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
 
47
  {%- endif -%}
special_tokens_map.json CHANGED
@@ -23,7 +23,6 @@
23
  "rstrip": false,
24
  "single_word": false
25
  },
26
- "sfr_token": "<start_function_response>",
27
  "unk_token": {
28
  "content": "<unk>",
29
  "lstrip": false,
 
23
  "rstrip": false,
24
  "single_word": false
25
  },
 
26
  "unk_token": {
27
  "content": "<unk>",
28
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
3
- size 33384899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
3
- size 4689144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff