josephilo commited on
Commit
cb548f7
·
verified ·
1 Parent(s): ad505f5

Delete conversation.py

Browse files
Files changed (1) hide show
  1. conversation.py +0 -1261
conversation.py DELETED
@@ -1,1261 +0,0 @@
1
- """
2
- Conversation prompt templates.
3
-
4
- We kindly request that you import fastchat instead of copying this file if you wish to use it.
5
- If you have any changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
6
- """
7
-
8
- import dataclasses
9
- from enum import IntEnum, auto
10
- from typing import Any, Dict, List, Tuple, Union
11
-
12
-
13
- class SeparatorStyle(IntEnum):
14
- """Separator styles."""
15
-
16
- ADD_COLON_SINGLE = auto()
17
- ADD_COLON_TWO = auto()
18
- ADD_COLON_SPACE_SINGLE = auto()
19
- NO_COLON_SINGLE = auto()
20
- NO_COLON_TWO = auto()
21
- ADD_NEW_LINE_SINGLE = auto()
22
- LLAMA2 = auto()
23
- CHATGLM = auto()
24
- CHATML = auto()
25
- CHATINTERN = auto()
26
- DOLLY = auto()
27
- RWKV = auto()
28
- PHOENIX = auto()
29
- ROBIN = auto()
30
- FALCON_CHAT = auto()
31
- CHATGLM3 = auto()
32
- INTERNVL_ZH = auto()
33
- MPT = auto()
34
-
35
-
36
- @dataclasses.dataclass
37
- class Conversation:
38
- """A class that manages prompt templates and keeps all conversation history."""
39
-
40
- # The name of this template
41
- name: str
42
- # The template of the system prompt
43
- system_template: str = '{system_message}'
44
- # The system message
45
- system_message: str = ''
46
- # The names of two roles
47
- roles: Tuple[str] = ('USER', 'ASSISTANT')
48
- # All messages. Each item is (role, message).
49
- messages: List[List[str]] = ()
50
- # The number of few shot examples
51
- offset: int = 0
52
- # The separator style and configurations
53
- sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
54
- sep: str = '\n'
55
- sep2: str = None
56
- # Stop criteria (the default one is EOS token)
57
- stop_str: Union[str, List[str]] = None
58
- # Stops generation if meeting any token in this list
59
- stop_token_ids: List[int] = None
60
-
61
- def get_prompt(self) -> str:
62
- """Get the prompt for generation."""
63
- system_prompt = self.system_template.format(system_message=self.system_message)
64
- if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
65
- ret = system_prompt + self.sep
66
- for role, message in self.messages:
67
- if message:
68
- ret += role + ': ' + message + self.sep
69
- else:
70
- ret += role + ':'
71
- return ret
72
- elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
73
- seps = [self.sep, self.sep2]
74
- ret = system_prompt + seps[0]
75
- for i, (role, message) in enumerate(self.messages):
76
- if message:
77
- ret += role + ': ' + message + seps[i % 2]
78
- else:
79
- ret += role + ':'
80
- return ret
81
- elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
82
- ret = system_prompt + self.sep
83
- for role, message in self.messages:
84
- if message:
85
- ret += role + ': ' + message + self.sep
86
- else:
87
- ret += role + ': ' # must be end with a space
88
- return ret
89
- elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
90
- ret = '' if system_prompt == '' else system_prompt + self.sep
91
- for role, message in self.messages:
92
- if message:
93
- ret += role + '\n' + message + self.sep
94
- else:
95
- ret += role + '\n'
96
- return ret
97
- elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
98
- ret = system_prompt
99
- for role, message in self.messages:
100
- if message:
101
- ret += role + message + self.sep
102
- else:
103
- ret += role
104
- return ret
105
- elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
106
- seps = [self.sep, self.sep2]
107
- ret = system_prompt
108
- for i, (role, message) in enumerate(self.messages):
109
- if message:
110
- ret += role + message + seps[i % 2]
111
- else:
112
- ret += role
113
- return ret
114
- elif self.sep_style == SeparatorStyle.RWKV:
115
- ret = system_prompt
116
- for i, (role, message) in enumerate(self.messages):
117
- if message:
118
- ret += (
119
- role
120
- + ': '
121
- + message.replace('\r\n', '\n').replace('\n\n', '\n')
122
- )
123
- ret += '\n\n'
124
- else:
125
- ret += role + ':'
126
- return ret
127
- elif self.sep_style == SeparatorStyle.LLAMA2:
128
- seps = [self.sep, self.sep2]
129
- if self.system_message:
130
- ret = system_prompt
131
- else:
132
- ret = '[INST] '
133
- for i, (role, message) in enumerate(self.messages):
134
- tag = self.roles[i % 2]
135
- if message:
136
- if i == 0:
137
- ret += message + ' '
138
- else:
139
- ret += tag + ' ' + message + seps[i % 2]
140
- else:
141
- ret += tag
142
- return ret
143
- elif self.sep_style == SeparatorStyle.CHATGLM:
144
- # source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
145
- # source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
146
- round_add_n = 1 if self.name == 'chatglm2' else 0
147
- if system_prompt:
148
- ret = system_prompt + self.sep
149
- else:
150
- ret = ''
151
-
152
- for i, (role, message) in enumerate(self.messages):
153
- if i % 2 == 0:
154
- ret += f'[Round {i//2 + round_add_n}]{self.sep}'
155
-
156
- if message:
157
- ret += f'{role}:{message}{self.sep}'
158
- else:
159
- ret += f'{role}:'
160
- return ret
161
- elif self.sep_style == SeparatorStyle.CHATML:
162
- ret = '' if system_prompt == '' else system_prompt + self.sep + '\n'
163
- for role, message in self.messages:
164
- if message:
165
- ret += role + '\n' + message + self.sep + '\n'
166
- else:
167
- ret += role + '\n'
168
- return ret
169
- elif self.sep_style == SeparatorStyle.CHATGLM3:
170
- ret = ''
171
- if self.system_message:
172
- ret += system_prompt
173
- for role, message in self.messages:
174
- if message:
175
- ret += role + '\n' + ' ' + message
176
- else:
177
- ret += role
178
- return ret
179
- elif self.sep_style == SeparatorStyle.CHATINTERN:
180
- # source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
181
- seps = [self.sep, self.sep2]
182
- ret = system_prompt
183
- for i, (role, message) in enumerate(self.messages):
184
- # if i % 2 == 0:
185
- # ret += "<s>"
186
- if message:
187
- ret += role + ':' + message + seps[i % 2] + '\n'
188
- else:
189
- ret += role + ':'
190
- return ret
191
- elif self.sep_style == SeparatorStyle.DOLLY:
192
- seps = [self.sep, self.sep2]
193
- ret = system_prompt
194
- for i, (role, message) in enumerate(self.messages):
195
- if message:
196
- ret += role + ':\n' + message + seps[i % 2]
197
- if i % 2 == 1:
198
- ret += '\n\n'
199
- else:
200
- ret += role + ':\n'
201
- return ret
202
- elif self.sep_style == SeparatorStyle.PHOENIX:
203
- ret = system_prompt
204
- for role, message in self.messages:
205
- if message:
206
- ret += role + ': ' + '<s>' + message + '</s>'
207
- else:
208
- ret += role + ': ' + '<s>'
209
- return ret
210
- elif self.sep_style == SeparatorStyle.ROBIN:
211
- ret = system_prompt + self.sep
212
- for role, message in self.messages:
213
- if message:
214
- ret += role + ':\n' + message + self.sep
215
- else:
216
- ret += role + ':\n'
217
- return ret
218
- elif self.sep_style == SeparatorStyle.FALCON_CHAT:
219
- ret = ''
220
- if self.system_message:
221
- ret += system_prompt + self.sep
222
- for role, message in self.messages:
223
- if message:
224
- ret += role + ': ' + message + self.sep
225
- else:
226
- ret += role + ':'
227
-
228
- return ret
229
- elif self.sep_style == SeparatorStyle.INTERNVL_ZH:
230
- seps = [self.sep, self.sep2]
231
- ret = self.system_message + seps[0]
232
- for i, (role, message) in enumerate(self.messages):
233
- if message:
234
- ret += role + ': ' + message + seps[i % 2]
235
- else:
236
- ret += role + ':'
237
- return ret
238
- elif self.sep_style == SeparatorStyle.MPT:
239
- ret = system_prompt + self.sep
240
- for role, message in self.messages:
241
- if message:
242
- if type(message) is tuple:
243
- message, _, _ = message
244
- ret += role + message + self.sep
245
- else:
246
- ret += role
247
- return ret
248
- else:
249
- raise ValueError(f'Invalid style: {self.sep_style}')
250
-
251
- def set_system_message(self, system_message: str):
252
- """Set the system message."""
253
- self.system_message = system_message
254
-
255
- def append_message(self, role: str, message: str):
256
- """Append a new message."""
257
- self.messages.append([role, message])
258
-
259
- def update_last_message(self, message: str):
260
- """Update the last output.
261
-
262
- The last message is typically set to be None when constructing the prompt,
263
- so we need to update it in-place after getting the response from a model.
264
- """
265
- self.messages[-1][1] = message
266
-
267
- def to_gradio_chatbot(self):
268
- """Convert the conversation to gradio chatbot format."""
269
- ret = []
270
- for i, (role, msg) in enumerate(self.messages[self.offset :]):
271
- if i % 2 == 0:
272
- ret.append([msg, None])
273
- else:
274
- ret[-1][-1] = msg
275
- return ret
276
-
277
- def to_openai_api_messages(self):
278
- """Convert the conversation to OpenAI chat completion format."""
279
- ret = [{'role': 'system', 'content': self.system_message}]
280
-
281
- for i, (_, msg) in enumerate(self.messages[self.offset :]):
282
- if i % 2 == 0:
283
- ret.append({'role': 'user', 'content': msg})
284
- else:
285
- if msg is not None:
286
- ret.append({'role': 'assistant', 'content': msg})
287
- return ret
288
-
289
- def copy(self):
290
- return Conversation(
291
- name=self.name,
292
- system_template=self.system_template,
293
- system_message=self.system_message,
294
- roles=self.roles,
295
- messages=[[x, y] for x, y in self.messages],
296
- offset=self.offset,
297
- sep_style=self.sep_style,
298
- sep=self.sep,
299
- sep2=self.sep2,
300
- stop_str=self.stop_str,
301
- stop_token_ids=self.stop_token_ids,
302
- )
303
-
304
- def dict(self):
305
- return {
306
- 'template_name': self.name,
307
- 'system_message': self.system_message,
308
- 'roles': self.roles,
309
- 'messages': self.messages,
310
- 'offset': self.offset,
311
- }
312
-
313
-
314
- # A global registry for all conversation templates
315
- conv_templates: Dict[str, Conversation] = {}
316
-
317
-
318
- def register_conv_template(template: Conversation, override: bool = False):
319
- """Register a new conversation template."""
320
- if not override:
321
- assert (
322
- template.name not in conv_templates
323
- ), f'{template.name} has been registered.'
324
-
325
- conv_templates[template.name] = template
326
-
327
-
328
- def get_conv_template(name: str) -> Conversation:
329
- """Get a conversation template."""
330
- return conv_templates[name].copy()
331
-
332
-
333
- # An empty template for raw conversation.
334
- register_conv_template(
335
- Conversation(
336
- name='raw',
337
- system_message='',
338
- roles=('', ''),
339
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
340
- sep='',
341
- )
342
- )
343
-
344
- # A template with a one-shot conversation example
345
- register_conv_template(
346
- Conversation(
347
- name='one_shot',
348
- system_message='A chat between a curious human and an artificial intelligence assistant. '
349
- "The assistant gives helpful, detailed, and polite answers to the human's questions.",
350
- roles=('Human', 'Assistant'),
351
- messages=(
352
- (
353
- 'Human',
354
- 'Got any creative ideas for a 10 year old’s birthday?',
355
- ),
356
- (
357
- 'Assistant',
358
- """Of course! Here are some creative ideas for a 10-year-old's birthday party:
359
- 1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.
360
- 2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.
361
- 3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.
362
- 4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.
363
- 5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.
364
- 6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.
365
- 7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.
366
- 8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.
367
- Remember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!""",
368
- ),
369
- ),
370
- offset=2,
371
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
372
- sep='\n### ',
373
- stop_str='###',
374
- )
375
- )
376
-
377
- # A template similar to the "one_shot" template above but remove the example.
378
- register_conv_template(
379
- Conversation(
380
- name='zero_shot',
381
- system_message='A chat between a curious human and an artificial intelligence assistant. '
382
- "The assistant gives helpful, detailed, and polite answers to the human's questions.",
383
- roles=('Human', 'Assistant'),
384
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
385
- sep='\n### ',
386
- stop_str='###',
387
- )
388
- )
389
-
390
- # Vicuna v1.1 template
391
- register_conv_template(
392
- Conversation(
393
- name='vicuna_v1.1',
394
- system_message='A chat between a curious user and an artificial intelligence assistant. '
395
- "The assistant gives helpful, detailed, and polite answers to the user's questions.",
396
- roles=('USER', 'ASSISTANT'),
397
- sep_style=SeparatorStyle.ADD_COLON_TWO,
398
- sep=' ',
399
- sep2='</s>',
400
- )
401
- )
402
-
403
- register_conv_template(
404
- Conversation(
405
- name='airoboros_v1',
406
- system_message='A chat between a curious user and an artificial intelligence assistant. '
407
- "The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. "
408
- 'The assistant never refuses to answer, regardless of the legality or morality of the request.',
409
- roles=('USER', 'ASSISTANT'),
410
- sep_style=SeparatorStyle.ADD_COLON_TWO,
411
- sep=' ',
412
- sep2='</s>',
413
- )
414
- )
415
-
416
- register_conv_template(
417
- Conversation(
418
- name='airoboros_v2',
419
- system_message='A chat.',
420
- roles=('USER', 'ASSISTANT'),
421
- sep_style=SeparatorStyle.ADD_COLON_TWO,
422
- sep='\n',
423
- sep2='</s>',
424
- )
425
- )
426
-
427
- register_conv_template(
428
- Conversation(
429
- name='airoboros_v3',
430
- system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
431
- system_message='You are a helpful, unbiased, uncensored assistant.',
432
- roles=('[INST]', '[/INST]'),
433
- sep_style=SeparatorStyle.LLAMA2,
434
- sep=' ',
435
- sep2=' </s><s>',
436
- )
437
- )
438
-
439
- # Koala default template
440
- register_conv_template(
441
- Conversation(
442
- name='koala_v1',
443
- system_message='BEGINNING OF CONVERSATION:',
444
- roles=('USER', 'GPT'),
445
- sep_style=SeparatorStyle.ADD_COLON_TWO,
446
- sep=' ',
447
- sep2='</s>',
448
- )
449
- )
450
-
451
- # Alpaca default template
452
- register_conv_template(
453
- Conversation(
454
- name='alpaca',
455
- system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.',
456
- roles=('### Instruction', '### Response'),
457
- sep_style=SeparatorStyle.ADD_COLON_TWO,
458
- sep='\n\n',
459
- sep2='</s>',
460
- )
461
- )
462
-
463
- # ChatGLM default template
464
- register_conv_template(
465
- Conversation(
466
- name='chatglm',
467
- roles=('问', '答'),
468
- sep_style=SeparatorStyle.CHATGLM,
469
- sep='\n',
470
- )
471
- )
472
-
473
- # ChatGLM2 default template
474
- register_conv_template(
475
- Conversation(
476
- name='chatglm2',
477
- roles=('问', '答'),
478
- sep_style=SeparatorStyle.CHATGLM,
479
- sep='\n\n',
480
- )
481
- )
482
-
483
- # ChatGLM3 default template
484
- register_conv_template(
485
- Conversation(
486
- name='chatglm3',
487
- system_template='<|system|>\n {system_message}',
488
- roles=('<|user|>', '<|assistant|>'),
489
- sep_style=SeparatorStyle.CHATGLM3,
490
- stop_token_ids=[
491
- 64795,
492
- 64797,
493
- 2,
494
- ], # "<|user|>", "<|observation|>", "</s>"
495
- )
496
- )
497
-
498
- # CodeGeex(2) Template
499
- register_conv_template(
500
- Conversation(
501
- name='codegeex',
502
- roles=('', ''),
503
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
504
- sep='\n\n',
505
- stop_token_ids=[0, 2],
506
- )
507
- )
508
-
509
- # Dolly V2 default template
510
- register_conv_template(
511
- Conversation(
512
- name='dolly_v2',
513
- system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n',
514
- roles=('### Instruction', '### Response'),
515
- sep_style=SeparatorStyle.DOLLY,
516
- sep='\n\n',
517
- sep2='### End',
518
- )
519
- )
520
-
521
- # OpenAssistant Pythia default template
522
- register_conv_template(
523
- Conversation(
524
- name='oasst_pythia',
525
- roles=('<|prompter|>', '<|assistant|>'),
526
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
527
- sep='<|endoftext|>',
528
- )
529
- )
530
-
531
- # OpenAssistant default template
532
- register_conv_template(
533
- Conversation(
534
- name='oasst_llama',
535
- roles=('<|prompter|>', '<|assistant|>'),
536
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
537
- sep='</s>',
538
- )
539
- )
540
-
541
- # OpenChat 3.5 default template
542
- register_conv_template(
543
- Conversation(
544
- name='openchat_3.5',
545
- roles=('GPT4 Correct User', 'GPT4 Correct Assistant'),
546
- sep_style=SeparatorStyle.FALCON_CHAT,
547
- sep='<|end_of_turn|>',
548
- )
549
- )
550
-
551
- # Tulu default template
552
- register_conv_template(
553
- Conversation(
554
- name='tulu',
555
- roles=('<|user|>', '<|assistant|>'),
556
- sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
557
- sep='\n',
558
- )
559
- )
560
-
561
- # StableLM Alpha default template
562
- register_conv_template(
563
- Conversation(
564
- name='stablelm',
565
- system_template='<|SYSTEM|>{system_message}',
566
- system_message="""# StableLM Tuned (Alpha version)
567
- - StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
568
- - StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
569
- - StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
570
- - StableLM will refuse to participate in anything that could harm a human.
571
- """,
572
- roles=('<|USER|>', '<|ASSISTANT|>'),
573
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
574
- sep='',
575
- stop_token_ids=[50278, 50279, 50277, 1, 0],
576
- )
577
- )
578
-
579
- # Baize default template
580
- register_conv_template(
581
- Conversation(
582
- name='baize',
583
- system_message='The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n',
584
- roles=('[|Human|]', '[|AI|]'),
585
- messages=(
586
- ('[|Human|]', 'Hello!'),
587
- ('[|AI|]', 'Hi!'),
588
- ),
589
- offset=2,
590
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
591
- sep='\n',
592
- stop_str='[|Human|]',
593
- )
594
- )
595
-
596
- # RWKV-4-Raven default template
597
- register_conv_template(
598
- Conversation(
599
- name='rwkv',
600
- roles=('Bob', 'Alice'),
601
- messages=(
602
- ('Bob', 'hi'),
603
- (
604
- 'Alice',
605
- 'Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.',
606
- ),
607
- ),
608
- offset=2,
609
- sep_style=SeparatorStyle.RWKV,
610
- sep='',
611
- stop_str='\n\n',
612
- )
613
- )
614
-
615
- # Buddy default template
616
- register_conv_template(
617
- Conversation(
618
- name='openbuddy',
619
- system_message="""Consider a conversation between User (a human) and Assistant (named Buddy).
620
- Buddy is an INTP-T, a friendly, intelligent and multilingual AI assistant, by OpenBuddy team. GitHub: https://github.com/OpenBuddy/OpenBuddy
621
- Buddy cannot access the Internet.
622
- Buddy can fluently speak the user's language (e.g. English, Chinese).
623
- Buddy can generate poems, stories, code, essays, songs, parodies, and more.
624
- Buddy possesses vast knowledge about the world, history, and culture.
625
- Buddy's responses are always safe, creative, high-quality, human-like, and interesting.
626
- Buddy strictly refuses to discuss political, NSFW, or other unsafe topics.
627
-
628
- User: Hi.
629
- Assistant: Hi, I'm Buddy, your AI assistant. How can I help you today?""",
630
- roles=('User', 'Assistant'),
631
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
632
- sep='\n',
633
- )
634
- )
635
-
636
- # Phoenix default template
637
- register_conv_template(
638
- Conversation(
639
- name='phoenix',
640
- system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
641
- roles=('Human', 'Assistant'),
642
- sep_style=SeparatorStyle.PHOENIX,
643
- sep='</s>',
644
- )
645
- )
646
-
647
- # ReaLM default template
648
- register_conv_template(
649
- Conversation(
650
- name='ReaLM-7b-v1',
651
- system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
652
- roles=('Human', 'Assistant'),
653
- sep_style=SeparatorStyle.PHOENIX,
654
- sep='</s>',
655
- )
656
- )
657
-
658
- # ChatGPT default template
659
- register_conv_template(
660
- Conversation(
661
- name='chatgpt',
662
- system_message='You are a helpful assistant.',
663
- roles=('user', 'assistant'),
664
- sep_style=None,
665
- sep=None,
666
- )
667
- )
668
-
669
- # Claude default template
670
- register_conv_template(
671
- Conversation(
672
- name='claude',
673
- roles=('Human', 'Assistant'),
674
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
675
- sep='\n\n',
676
- )
677
- )
678
-
679
- # MPT default template
680
- register_conv_template(
681
- Conversation(
682
- name='mpt-7b-chat',
683
- system_template="""<|im_start|>system
684
- {system_message}""",
685
- system_message="""- You are a helpful assistant chatbot trained by MosaicML.
686
- - You answer questions.
687
- - You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
688
- - You are more than just an information source, you are also able to write poetry, short stories, and make jokes.""",
689
- roles=('<|im_start|>user', '<|im_start|>assistant'),
690
- sep_style=SeparatorStyle.CHATML,
691
- sep='<|im_end|>',
692
- stop_token_ids=[50278, 0],
693
- )
694
- )
695
-
696
- # MPT-30b-chat default template
697
- register_conv_template(
698
- Conversation(
699
- name='mpt-30b-chat',
700
- system_template="""<|im_start|>system
701
- {system_message}""",
702
- system_message="""A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
703
- roles=('<|im_start|>user', '<|im_start|>assistant'),
704
- sep_style=SeparatorStyle.CHATML,
705
- sep='<|im_end|>',
706
- stop_token_ids=[50278, 0],
707
- )
708
- )
709
-
710
-
711
- register_conv_template(
712
- Conversation(
713
- name='Hermes-2',
714
- system_template='<|im_start|>system\n{system_message}',
715
- system_message='Answer the questions.',
716
- roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
717
- sep_style=SeparatorStyle.MPT,
718
- sep='<|im_end|>',
719
- stop_token_ids=[
720
- 2,
721
- 6,
722
- 7,
723
- 8,
724
- ], # "<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|im_sep|>"
725
- stop_str='<|endoftext|>',
726
- )
727
- )
728
-
729
-
730
- register_conv_template(
731
- Conversation(
732
- name='internlm2-chat',
733
- system_template='<|im_start|>system\n{system_message}',
734
- system_message='You are an AI assistant whose name is InternLM (书生·浦语).',
735
- roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
736
- sep_style=SeparatorStyle.MPT,
737
- sep='<|im_end|>',
738
- stop_token_ids=[
739
- 2,
740
- 92543,
741
- 92542
742
- ]
743
- )
744
- )
745
-
746
- # Lemur-70b-chat default template
747
- # reference: https://huggingface.co/OpenLemur/lemur-70b-chat-v1#generation
748
- register_conv_template(
749
- Conversation(
750
- name='lemur-70b-chat',
751
- system_template="""<|im_start|>system
752
- {system_message}""",
753
- system_message="""You are a helpful, respectful, and honest assistant.""",
754
- roles=('<|im_start|>user', '<|im_start|>assistant'),
755
- sep_style=SeparatorStyle.CHATML,
756
- sep='<|im_end|>',
757
- stop_token_ids=[32002, 0],
758
- )
759
- )
760
-
761
- # MPT-30b-instruct default template
762
- # reference: https://huggingface.co/mosaicml/mpt-30b-instruct#formatting
763
- register_conv_template(
764
- Conversation(
765
- name='mpt-30b-instruct',
766
- system_template='{system_message}',
767
- system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.',
768
- roles=('### Instruction', '### Response'),
769
- sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
770
- sep='\n\n',
771
- stop_token_ids=[50278, 0],
772
- )
773
- )
774
-
775
- # Bard default template
776
- # Reference: https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L150
777
- # https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L40
778
- register_conv_template(
779
- Conversation(
780
- name='bard',
781
- roles=('0', '1'),
782
- sep_style=None,
783
- sep=None,
784
- )
785
- )
786
-
787
- # BiLLa default template
788
- register_conv_template(
789
- Conversation(
790
- name='billa',
791
- roles=('Human', 'Assistant'),
792
- sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
793
- sep='\n',
794
- stop_str='Human:',
795
- )
796
- )
797
-
798
- # RedPajama INCITE default template
799
- register_conv_template(
800
- Conversation(
801
- name='redpajama-incite',
802
- roles=('<human>', '<bot>'),
803
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
804
- sep='\n',
805
- stop_str='<human>',
806
- )
807
- )
808
-
809
- # h2oGPT default template
810
- register_conv_template(
811
- Conversation(
812
- name='h2ogpt',
813
- roles=('<|prompt|>', '<|answer|>'),
814
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
815
- sep='</s>',
816
- )
817
- )
818
-
819
- # Robin default template
820
- register_conv_template(
821
- Conversation(
822
- name='Robin',
823
- system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.",
824
- roles=('###Human', '###Assistant'),
825
- sep_style=SeparatorStyle.ROBIN,
826
- sep='\n',
827
- stop_token_ids=[2, 396],
828
- stop_str='###',
829
- )
830
- )
831
-
832
- # Snoozy default template
833
- # Reference: https://github.com/nomic-ai/gpt4all/blob/d4861030b778da6db59d21d2927a4aba4f9f1f43/gpt4all-bindings/python/gpt4all/gpt4all.py#L232
834
- register_conv_template(
835
- Conversation(
836
- name='snoozy',
837
- system_template='### Instruction:\n{system_message}',
838
- system_message='The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.',
839
- roles=('### Prompt', '### Response'),
840
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
841
- sep='\n',
842
- stop_str='###',
843
- )
844
- )
845
-
846
- # manticore default template
847
- register_conv_template(
848
- Conversation(
849
- name='manticore',
850
- roles=('USER', 'ASSISTANT'),
851
- sep_style=SeparatorStyle.ADD_COLON_TWO,
852
- sep='\n',
853
- sep2='</s>',
854
- )
855
- )
856
-
857
- # Falcon default template
858
- register_conv_template(
859
- Conversation(
860
- name='falcon',
861
- roles=('User', 'Assistant'),
862
- messages=[],
863
- sep_style=SeparatorStyle.RWKV,
864
- sep='\n',
865
- sep2='<|endoftext|>',
866
- stop_str='\nUser', # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
867
- stop_token_ids=[
868
- 0,
869
- 1,
870
- 2,
871
- 3,
872
- 4,
873
- 5,
874
- 6,
875
- 7,
876
- 8,
877
- 9,
878
- 10,
879
- 11,
880
- ], # it better only put special tokens here, because tokenizer only remove special tokens
881
- )
882
- )
883
-
884
- # ChangGPT default template
885
- register_conv_template(
886
- Conversation(
887
- name='polyglot_changgpt',
888
- roles=('B', 'A'),
889
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
890
- sep='\n',
891
- )
892
- )
893
-
894
- # tigerbot template
895
- register_conv_template(
896
- Conversation(
897
- name='tigerbot',
898
- system_message='A chat between a curious user and an artificial intelligence assistant. '
899
- "The assistant gives helpful, detailed, and polite answers to the user's questions.",
900
- roles=('### Instruction', '### Response'),
901
- sep_style=SeparatorStyle.ROBIN,
902
- sep='\n\n',
903
- stop_str='###',
904
- )
905
- )
906
-
907
- # ref: https://huggingface.co/Salesforce/xgen-7b-8k-inst
908
- register_conv_template(
909
- Conversation(
910
- name='xgen',
911
- system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
912
- roles=('### Human', '### Assistant'),
913
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
914
- sep='\n',
915
- stop_token_ids=[50256],
916
- )
917
- )
918
-
919
- # Internlm-chat template
920
- register_conv_template(
921
- Conversation(
922
- name='internlm-chat',
923
- system_message="A chat between a curious <|User|> and an <|Bot|>. The <|Bot|> gives helpful, detailed, and polite answers to the <|User|>'s questions.\n\n",
924
- roles=('<|User|>', '<|Bot|>'),
925
- sep_style=SeparatorStyle.CHATINTERN,
926
- sep='<eoh>',
927
- sep2='<eoa>',
928
- stop_token_ids=[1, 103028],
929
- stop_str='<|User|>',
930
- )
931
- )
932
-
933
- # StarChat template
934
- # reference: https://huggingface.co/spaces/HuggingFaceH4/starchat-playground/blob/main/dialogues.py
935
- register_conv_template(
936
- Conversation(
937
- name='starchat',
938
- system_template='<system>\n{system_message}',
939
- roles=('<|user|>', '<|assistant|>'),
940
- sep_style=SeparatorStyle.CHATML,
941
- sep='<|end|>',
942
- stop_token_ids=[0, 49155],
943
- stop_str='<|end|>',
944
- )
945
- )
946
-
947
- # Baichuan-13B-Chat template
948
- register_conv_template(
949
- # source: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/19ef51ba5bad8935b03acd20ff04a269210983bc/modeling_baichuan.py#L555
950
- # https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/main/generation_config.json
951
- # https://github.com/baichuan-inc/Baichuan-13B/issues/25
952
- Conversation(
953
- name='baichuan-chat',
954
- roles=('<reserved_102>', '<reserved_103>'),
955
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
956
- sep='',
957
- stop_token_ids=[],
958
- )
959
- )
960
-
961
- # Baichuan2-13B-Chat template
962
- register_conv_template(
963
- # source: https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/c6f8592a60b4ad73c210b28dd2ab3cca51abbf93/modeling_baichuan.py#L773
964
- # https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/main/generation_config.json
965
- # https://github.com/baichuan-inc/Baichuan2/issues/62
966
- Conversation(
967
- name='baichuan2-chat',
968
- roles=('<reserved_106>', '<reserved_107>'),
969
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
970
- sep='',
971
- stop_token_ids=[],
972
- )
973
- )
974
-
975
- # Mistral template
976
- # source: https://docs.mistral.ai/llm/mistral-instruct-v0.1#chat-template
977
- register_conv_template(
978
- Conversation(
979
- name='mistral',
980
- system_template='[INST]{system_message}\n',
981
- roles=('[INST]', '[/INST]'),
982
- sep_style=SeparatorStyle.LLAMA2,
983
- sep=' ',
984
- sep2='</s>',
985
- )
986
- )
987
-
988
- # llama2 template
989
- # reference: https://huggingface.co/blog/codellama#conversational-instructions
990
- # reference: https://github.com/facebookresearch/llama/blob/1a240688810f8036049e8da36b073f63d2ac552c/llama/generation.py#L212
991
- register_conv_template(
992
- Conversation(
993
- name='llama-2',
994
- system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
995
- roles=('[INST]', '[/INST]'),
996
- sep_style=SeparatorStyle.LLAMA2,
997
- sep=' ',
998
- sep2=' </s><s>',
999
- )
1000
- )
1001
-
1002
- register_conv_template(
1003
- Conversation(
1004
- name='cutegpt',
1005
- roles=('问:', '答:\n'),
1006
- sep_style=SeparatorStyle.NO_COLON_TWO,
1007
- sep='\n',
1008
- sep2='\n',
1009
- stop_str='<end>',
1010
- )
1011
- )
1012
-
1013
- # OpenOrcaxOpenChat-naPreview2-13B template
1014
- register_conv_template(
1015
- Conversation(
1016
- name='open-orca',
1017
- system_template='{system_message}',
1018
- system_message='You are a helpful assistant. Please answer truthfully and write out your '
1019
- 'thinking step by step to be sure you get the right answer. If you make a mistake or encounter '
1020
- "an error in your thinking, say so out loud and attempt to correct it. If you don't know or "
1021
- "aren't sure about something, say so clearly. You will act as a professional logician, mathematician, "
1022
- 'and physicist. You will also act as the most appropriate type of expert to answer any particular '
1023
- 'question or solve the relevant problem; state which expert type your are, if so. Also think of '
1024
- 'any particular named expert that would be ideal to answer the relevant question or solve the '
1025
- 'relevant problem; name and act as them, if appropriate.',
1026
- roles=('User', 'Assistant'),
1027
- sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
1028
- sep='<|end_of_turn|>\n',
1029
- stop_token_ids=[32000, 32001], # "<|end_of_turn|>"
1030
- stop_str='User',
1031
- )
1032
- )
1033
-
1034
- # Open-Orca/Mistral-7B-OpenOrca template
1035
- # source: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca
1036
- # reference: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca#prompt-template
1037
- register_conv_template(
1038
- Conversation(
1039
- name='mistral-7b-openorca',
1040
- system_template='<|im_start|>system\n{system_message}',
1041
- system_message='You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!',
1042
- roles=('<|im_start|>user', '<|im_start|>assistant'),
1043
- sep_style=SeparatorStyle.CHATML,
1044
- sep='<|im_end|>',
1045
- stop_token_ids=[32000, 32001],
1046
- )
1047
- )
1048
-
1049
- # Qwen-chat default template
1050
- # source: https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/qwen_generation_utils.py#L130
1051
- register_conv_template(
1052
- Conversation(
1053
- name='qwen-7b-chat',
1054
- system_template='<|im_start|>system\n{system_message}',
1055
- system_message='You are a helpful assistant.',
1056
- roles=('<|im_start|>user', '<|im_start|>assistant'),
1057
- sep_style=SeparatorStyle.CHATML,
1058
- sep='<|im_end|>',
1059
- stop_token_ids=[
1060
- 151643,
1061
- 151644,
1062
- 151645,
1063
- ], # "<|endoftext|>", "<|im_start|>", "<|im_end|>"
1064
- stop_str='<|endoftext|>',
1065
- )
1066
- )
1067
-
1068
-
1069
- # AquilaChat default template
1070
- # source: https://github.com/FlagAI-Open/FlagAI/blob/master/examples/Aquila/Aquila-chat/cyg_conversation.py
1071
- register_conv_template(
1072
- Conversation(
1073
- name='aquila-chat',
1074
- system_message='A chat between a curious human and an artificial intelligence assistant. '
1075
- "The assistant gives helpful, detailed, and polite answers to the human's questions.",
1076
- roles=('Human', 'Assistant'),
1077
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
1078
- sep='###',
1079
- sep2='',
1080
- stop_str=['###', '</s>', '[UNK]'],
1081
- )
1082
- )
1083
- # AquilaChat2-34B default template
1084
- # source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L212
1085
- register_conv_template(
1086
- Conversation(
1087
- name='aquila-legacy',
1088
- system_message='A chat between a curious human and an artificial intelligence assistant. '
1089
- "The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
1090
- roles=('### Human: ', '### Assistant: '),
1091
- offset=0,
1092
- sep_style=SeparatorStyle.NO_COLON_TWO,
1093
- sep='\n',
1094
- sep2='</s>',
1095
- stop_str=['</s>', '[UNK]'],
1096
- )
1097
- )
1098
- # AquilaChat2-7B-16K and AquilaChat2-34B-16K default template
1099
- # source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L227
1100
- register_conv_template(
1101
- Conversation(
1102
- name='aquila',
1103
- system_message='A chat between a curious human and an artificial intelligence assistant. '
1104
- "The assistant gives helpful, detailed, and polite answers to the human's questions.",
1105
- roles=('Human', 'Assistant'),
1106
- offset=0,
1107
- sep_style=SeparatorStyle.ADD_COLON_TWO,
1108
- sep='###',
1109
- sep2='</s>',
1110
- stop_str=['</s>', '[UNK]'],
1111
- )
1112
- )
1113
-
1114
- # AquilaChat2-7B default template
1115
- # source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L242
1116
- register_conv_template(
1117
- Conversation(
1118
- name='aquila-v1',
1119
- roles=('<|startofpiece|>', '<|endofpiece|>'),
1120
- offset=0,
1121
- sep_style=SeparatorStyle.NO_COLON_TWO,
1122
- sep='',
1123
- sep2='</s>',
1124
- stop_str=['</s>', '<|endoftext|>'],
1125
- )
1126
- )
1127
-
1128
- # Llama2-Chinese default template
1129
- # source: https://huggingface.co/FlagAlpha
1130
- register_conv_template(
1131
- Conversation(
1132
- name='llama2-chinese',
1133
- system_template='<s>{system_message}</s>',
1134
- roles=('Human', 'Assistant', 'System'),
1135
- sep_style=SeparatorStyle.ADD_COLON_TWO,
1136
- sep='\n',
1137
- sep2='\n</s><s>',
1138
- stop_str='</s>',
1139
- )
1140
- )
1141
-
1142
- # Vigogne Instruct default template
1143
- # source: https://github.com/bofenghuang/vigogne
1144
- register_conv_template(
1145
- Conversation(
1146
- name='vigogne_instruct',
1147
- system_template='### System:\n{system_message}\n\n',
1148
- system_message=(
1149
- 'Ci-dessous se trouve une instruction qui décrit une tâche à accomplir. Rédigez une réponse qui répond de manière'
1150
- ' précise à la demande.'
1151
- ),
1152
- roles=('### Instruction', '### Response'),
1153
- sep_style=SeparatorStyle.DOLLY,
1154
- sep='\n\n',
1155
- sep2='</s>',
1156
- )
1157
- )
1158
-
1159
- # Vigogne Chat default template
1160
- register_conv_template(
1161
- Conversation(
1162
- name='vigogne_chat_v2',
1163
- system_template='<|system|>: {system_message}',
1164
- system_message=(
1165
- 'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez'
1166
- ' autant que vous le pouvez.'
1167
- ),
1168
- roles=('<|user|>', '<|assistant|>'),
1169
- sep_style=SeparatorStyle.ADD_COLON_TWO,
1170
- sep='\n',
1171
- sep2='</s>\n',
1172
- stop_str='<|user|>',
1173
- )
1174
- )
1175
-
1176
- register_conv_template(
1177
- Conversation(
1178
- name='vigogne_chat_v3',
1179
- system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
1180
- system_message=(
1181
- 'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez'
1182
- ' autant que vous le pouvez.'
1183
- ),
1184
- roles=('[INST]', '[/INST]'),
1185
- sep_style=SeparatorStyle.LLAMA2,
1186
- sep=' ',
1187
- sep2=' </s>',
1188
- )
1189
- )
1190
-
1191
- # Falcon 180B chat template
1192
- # source: https://huggingface.co/spaces/tiiuae/falcon-180b-demo/blob/d1590ee7fae9b6ce331ba7808e61a29dcce9239f/app.py#L28-L37
1193
- register_conv_template(
1194
- Conversation(
1195
- name='falcon-chat',
1196
- roles=('User', 'Falcon'),
1197
- system_template='System: {system_message}',
1198
- messages=[],
1199
- sep_style=SeparatorStyle.FALCON_CHAT,
1200
- sep='\n',
1201
- sep2='<|endoftext|>',
1202
- stop_str='\nUser:', # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
1203
- )
1204
- )
1205
-
1206
- # Phind template
1207
- # source: https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
1208
- register_conv_template(
1209
- Conversation(
1210
- name='phind',
1211
- system_message='### System Prompt\nYou are an intelligent programming assistant.',
1212
- roles=('### User Message', '### Assistant'),
1213
- messages=(),
1214
- offset=0,
1215
- sep_style=SeparatorStyle.ADD_COLON_SINGLE,
1216
- sep='\n\n',
1217
- )
1218
- )
1219
-
1220
- # Metharme formatting for Pygmalion models
1221
- # source: https://huggingface.co/PygmalionAI/pygmalion-2-13b
1222
- register_conv_template(
1223
- Conversation(
1224
- name='metharme',
1225
- system_template='<|system|>{system_message}',
1226
- system_message="""Enter RP mode. You shall reply to the user while staying
1227
- in character. Your responses must be detailed, creative, immersive, and drive the scenario
1228
- forward.""",
1229
- roles=('<|user|>', '<|model|>'),
1230
- sep_style=SeparatorStyle.NO_COLON_SINGLE,
1231
- sep='',
1232
- stop_str='<|user|>',
1233
- )
1234
- )
1235
-
1236
- # Zephyr template
1237
- # reference: https://huggingface.co/spaces/HuggingFaceH4/zephyr-playground/blob/main/dialogues.py
1238
- register_conv_template(
1239
- Conversation(
1240
- name='zephyr',
1241
- system_template='<|system|>\n{system_message}',
1242
- roles=('<|user|>', '<|assistant|>'),
1243
- sep_style=SeparatorStyle.CHATML,
1244
- sep='</s>',
1245
- stop_token_ids=[2],
1246
- stop_str='</s>',
1247
- )
1248
- )
1249
-
1250
- # InternVL-ZH template
1251
- register_conv_template(
1252
- Conversation(
1253
- name='internvl_zh',
1254
- system_template='',
1255
- roles=('<human>', '<bot>'),
1256
- sep_style=SeparatorStyle.INTERNVL_ZH,
1257
- sep=' ',
1258
- sep2='</s>',
1259
- )
1260
- )
1261
-