File size: 16,359 Bytes
d0a2875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<PAD>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<UNK>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<CLS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<SEP>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<MASK_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<BOS_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<EOS_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<EOP_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "255000": {
      "content": "<|START_OF_TURN_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255001": {
      "content": "<|END_OF_TURN_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "255002": {
      "content": "<|YES_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255003": {
      "content": "<|NO_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255004": {
      "content": "<|GOOD_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255005": {
      "content": "<|BAD_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255006": {
      "content": "<|USER_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255007": {
      "content": "<|CHATBOT_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255008": {
      "content": "<|SYSTEM_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255009": {
      "content": "<|USER_0_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255010": {
      "content": "<|USER_1_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255011": {
      "content": "<|USER_2_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255012": {
      "content": "<|USER_3_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255013": {
      "content": "<|USER_4_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255014": {
      "content": "<|USER_5_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255015": {
      "content": "<|USER_6_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255016": {
      "content": "<|USER_7_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255017": {
      "content": "<|USER_8_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255018": {
      "content": "<|USER_9_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255019": {
      "content": "<|EXTRA_0_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255020": {
      "content": "<|EXTRA_1_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255021": {
      "content": "<|EXTRA_2_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255022": {
      "content": "<|EXTRA_3_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255023": {
      "content": "<|EXTRA_4_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255024": {
      "content": "<|EXTRA_5_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255025": {
      "content": "<|EXTRA_6_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255026": {
      "content": "<|EXTRA_7_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255027": {
      "content": "<|EXTRA_8_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "255028": {
      "content": "<|EXTRA_9_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<BOS_TOKEN>",
  "chat_template": [
    {
      "name": "default",
      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
    },
    {
      "name": "tool_use",
      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n    \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n    Args:\n        '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n        ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n    \"\"\"\n    pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n    {\n        \"tool_name\": title of the tool in the specification,\n        \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n    }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
    },
    {
      "name": "rag",
      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
    }
  ],
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|END_OF_TURN_TOKEN|>",
  "legacy": true,
  "merges_file": null,
  "model_max_length": 2048,
  "pad_token": "<PAD>",
  "padding_side": "right",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "CohereTokenizer",
  "unk_token": "null",
  "use_default_system_prompt": false,
  "use_fast": true,
  "vocab_file": null
}