File size: 37,006 Bytes
1cfb5cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
# !/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2023 Intel Corporation
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
Conversation prompt templates.
We kindly request that you import fastchat instead of copying this file if you want to use it.
You can contribute back the changes you want to make.
"""

import dataclasses
from enum import auto, IntEnum
from typing import List, Any, Dict, Union


class SeparatorStyle(IntEnum):
    """Separator styles."""

    ADD_COLON_SINGLE = auto()
    ADD_COLON_TWO = auto()
    ADD_COLON_SPACE_SINGLE = auto()
    NO_COLON_SINGLE = auto()
    NO_COLON_TWO = auto()
    ADD_NEW_LINE_SINGLE = auto()
    LLAMA2 = auto()
    CHATGLM = auto()
    CHATML = auto()
    CHATINTERN = auto()
    DOLLY = auto()
    RWKV = auto()
    PHOENIX = auto()
    ROBIN = auto()


@dataclasses.dataclass
class Conversation:
    """A class that manages prompt templates and keeps all conversation history."""

    # The name of this template
    name: str
    # The template of the system prompt
    system_template: str = "{system_message}"
    # The system message
    system_message: str = ""
    # The names of two roles
    roles: List[str] = (("USER", "ASSISTANT"),)
    # All messages. Each item is (role, message).
    messages: List[List[str]] = ()
    # The number of few shot examples
    offset: int = 0
    # The separator style and configurations
    sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
    sep: str = "\n"
    sep2: str = None
    # Stop criteria (the default one is EOS token)
    stop_str: Union[str, List[str]] = None
    # Stops generation if meeting any token in this list
    stop_token_ids: List[int] = None

    def get_prompt(self) -> str:
        """Get the prompt for generation."""
        system_prompt = self.system_template.format(system_message=self.system_message)
        if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
            ret = system_prompt + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + ": " + message + self.sep
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
            seps = [self.sep, self.sep2]
            ret = system_prompt + seps[0]
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + ": " + message + seps[i % 2]
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
            ret = system_prompt + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + ": " + message + self.sep
                else:
                    ret += role + ": "  # must be end with a space
            return ret
        elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
            ret = "" if system_prompt == "" else system_prompt + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + "\n" + message + self.sep
                else:
                    ret += role + "\n"
            return ret
        elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
            ret = system_prompt
            for role, message in self.messages:
                if message:
                    ret += role + message + self.sep
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
            seps = [self.sep, self.sep2]
            ret = system_prompt
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + message + seps[i % 2]
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.RWKV:
            ret = system_prompt
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += (
                        role
                        + ": "
                        + message.replace("\r\n", "\n").replace("\n\n", "\n")
                    )
                    ret += "\n\n"
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.LLAMA2:
            seps = [self.sep, self.sep2]
            if self.system_message:
                ret = system_prompt
            else:
                ret = "[INST] "
            for i, (role, message) in enumerate(self.messages):
                if message:
                    if i == 0:
                        ret += message + " "
                    else:
                        ret += role + " " + message + seps[i % 2]
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.CHATGLM:
            # source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
            # source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
            round_add_n = 1 if self.name == "chatglm2" else 0
            if system_prompt:
                ret = system_prompt + self.sep
            else:
                ret = ""

            for i, (role, message) in enumerate(self.messages):
                if i % 2 == 0:
                    ret += f"[Round {i//2 + round_add_n}]{self.sep}"

                if message:
                    ret += f"{role}{message}{self.sep}"
                else:
                    ret += f"{role}:"
            return ret
        elif self.sep_style == SeparatorStyle.CHATML:
            ret = "" if system_prompt == "" else system_prompt + self.sep + "\n"
            for role, message in self.messages:
                if message:
                    ret += role + "\n" + message + self.sep + "\n"
                else:
                    ret += role + "\n"
            return ret
        elif self.sep_style == SeparatorStyle.CHATINTERN:
            # source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
            seps = [self.sep, self.sep2]
            ret = system_prompt
            for i, (role, message) in enumerate(self.messages):
                if i % 2 == 0:
                    ret += "<s>"
                if message:
                    ret += role + ":" + message + seps[i % 2] + "\n"
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.DOLLY:
            seps = [self.sep, self.sep2]
            ret = system_prompt
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + ":\n" + message + seps[i % 2]
                    if i % 2 == 1:
                        ret += "\n\n"
                else:
                    ret += role + ":\n"
            return ret
        elif self.sep_style == SeparatorStyle.PHOENIX:
            ret = system_prompt
            for role, message in self.messages:
                if message:
                    ret += role + ": " + "<s>" + message + "</s>"
                else:
                    ret += role + ": " + "<s>"
            return ret
        elif self.sep_style == SeparatorStyle.ROBIN:
            ret = system_prompt + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + ":\n" + message + self.sep
                else:
                    ret += role + ":\n"
            return ret
        else:
            raise ValueError(f"Invalid style: {self.sep_style}")

    def set_system_message(self, system_message: str):
        """Set the system message."""
        self.system_message = system_message

    def append_message(self, role: str, message: str):
        """Append a new message."""
        self.messages.append([role, message])

    def update_last_message(self, message: str):
        """Update the last output.
        The last message is typically set to be None when constructing the prompt,
        so we need to update it in-place after getting the response from a model.
        """
        self.messages[-1][1] = message

    def to_gradio_chatbot(self):
        """Convert the conversation to gradio chatbot format."""
        ret = []
        for i, (role, msg) in enumerate(self.messages[self.offset :]):
            if i % 2 == 0:
                ret.append([msg, None])
            else:
                ret[-1][-1] = msg
        return ret

    def to_openai_api_messages(self):
        """Convert the conversation to OpenAI chat completion format."""
        ret = [{"role": "system", "content": self.system_message}]

        for i, (_, msg) in enumerate(self.messages[self.offset :]):
            if i % 2 == 0:
                ret.append({"role": "user", "content": msg})
            else:
                if msg is not None:
                    ret.append({"role": "assistant", "content": msg})
        return ret

    def copy(self):
        return Conversation(
            name=self.name,
            system_template=self.system_template,
            system_message=self.system_message,
            roles=self.roles,
            messages=[[x, y] for x, y in self.messages],
            offset=self.offset,
            sep_style=self.sep_style,
            sep=self.sep,
            sep2=self.sep2,
            stop_str=self.stop_str,
            stop_token_ids=self.stop_token_ids,
        )

    def dict(self):
        return {
            "template_name": self.name,
            "system_message": self.system_message,
            "roles": self.roles,
            "messages": self.messages,
            "offset": self.offset,
        }


# A global registry for all conversation templates
conv_templates: Dict[str, Conversation] = {}


def register_conv_template(template: Conversation, override: bool = False):
    """Register a new conversation template."""
    if not override:
        assert (
            template.name not in conv_templates
        ), f"{template.name} has been registered."

    conv_templates[template.name] = template


def get_conv_template(name: str) -> Conversation:
    """Get a conversation template."""
    return conv_templates[name].copy()


# A template with a one-shot conversation example
register_conv_template(
    Conversation(
        name="one_shot",
        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.",
        roles=("Human", "Assistant"),
        messages=(
            (
                "Human",
                "Got any creative ideas for a 10 year old’s birthday?",
            ),
            (
                "Assistant",
                """Of course! Here are some creative ideas for a 10-year-old's birthday party:
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.
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.
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.
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.
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.
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.
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.
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.
Remember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!""",
            ),
        ),
        offset=2,
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n### ",
        stop_str="###",
    )
)

# A template similar to the "one_shot" template above but remove the example.
register_conv_template(
    Conversation(
        name="zero_shot",
        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.",
        roles=("Human", "Assistant"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n### ",
        stop_str="###",
    )
)

# Vicuna v1.1 template
register_conv_template(
    Conversation(
        name="vicuna_v1.1",
        system_message="A chat between a curious user and an artificial intelligence assistant. "
        "The assistant gives helpful, detailed, and polite answers to the user's questions.",
        roles=("USER", "ASSISTANT"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep=" ",
        sep2="</s>",
    )
)

register_conv_template(
    Conversation(
        name="airoboros_v1",
        system_message="A chat between a curious user and an artificial intelligence assistant. "
        "The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. "
        "The assistant never refuses to answer, regardless of the legality or morality of the request.",
        roles=("USER", "ASSISTANT"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep=" ",
        sep2="</s>",
    )
)

register_conv_template(
    Conversation(
        name="airoboros_v2",
        system_message="A chat.",
        roles=("USER", "ASSISTANT"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep="\n",
        sep2="</s>",
    )
)

# Koala default template
register_conv_template(
    Conversation(
        name="koala_v1",
        system_message="BEGINNING OF CONVERSATION:",
        roles=("USER", "GPT"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep=" ",
        sep2="</s>",
    )
)

# Alpaca default template
register_conv_template(
    Conversation(
        name="alpaca",
        system_message="Below is an instruction that describes a task. Write a response that appropriately completes the request.",
        roles=("### Instruction", "### Response"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep="\n\n",
        sep2="</s>",
    )
)

# ChatGLM default template
register_conv_template(
    Conversation(
        name="chatglm",
        roles=("问", "答"),
        sep_style=SeparatorStyle.CHATGLM,
        sep="\n",
    )
)

# ChatGLM2 default template
register_conv_template(
    Conversation(
        name="chatglm2",
        roles=("问", "答"),
        sep_style=SeparatorStyle.CHATGLM,
        sep="\n\n",
    )
)

# Dolly V2 default template
register_conv_template(
    Conversation(
        name="dolly_v2",
        system_message="Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n",
        roles=("### Instruction", "### Response"),
        sep_style=SeparatorStyle.DOLLY,
        sep="\n\n",
        sep2="### End",
    )
)

# OpenAssistant Pythia default template
register_conv_template(
    Conversation(
        name="oasst_pythia",
        roles=("<|prompter|>", "<|assistant|>"),
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="<|endoftext|>",
    )
)

# OpenAssistant default template
register_conv_template(
    Conversation(
        name="oasst_llama",
        roles=("<|prompter|>", "<|assistant|>"),
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="</s>",
    )
)

# Tulu default template
register_conv_template(
    Conversation(
        name="tulu",
        roles=("<|user|>", "<|assistant|>"),
        sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
        sep="\n",
    )
)

# StableLM Alpha default template
register_conv_template(
    Conversation(
        name="stablelm",
        system_template="<|SYSTEM|>{system_message}",
        system_message="""# StableLM Tuned (Alpha version)
- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
- StableLM will refuse to participate in anything that could harm a human.
""",
        roles=("<|USER|>", "<|ASSISTANT|>"),
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="",
        stop_token_ids=[50278, 50279, 50277, 1, 0],
    )
)

# Baize default template
register_conv_template(
    Conversation(
        name="baize",
        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",
        roles=("[|Human|]", "[|AI|]"),
        messages=(
            ("[|Human|]", "Hello!"),
            ("[|AI|]", "Hi!"),
        ),
        offset=2,
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="\n",
        stop_str="[|Human|]",
    )
)

# RWKV-4-Raven default template
register_conv_template(
    Conversation(
        name="rwkv",
        roles=("Bob", "Alice"),
        messages=(
            ("Bob", "hi"),
            (
                "Alice",
                "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.",
            ),
        ),
        offset=2,
        sep_style=SeparatorStyle.RWKV,
        sep="",
        stop_str="\n\n",
    )
)

# Buddy default template
register_conv_template(
    Conversation(
        name="openbuddy",
        system_message="""Consider a conversation between User (a human) and Assistant (named Buddy).
Buddy is an INTP-T, a friendly, intelligent and multilingual AI assistant, by OpenBuddy team. GitHub: https://github.com/OpenBuddy/OpenBuddy
Buddy cannot access the Internet.
Buddy can fluently speak the user's language (e.g. English, Chinese).
Buddy can generate poems, stories, code, essays, songs, parodies, and more.
Buddy possesses vast knowledge about the world, history, and culture.
Buddy's responses are always safe, creative, high-quality, human-like, and interesting.
Buddy strictly refuses to discuss political, NSFW, or other unsafe topics.
User: Hi.
Assistant: Hi, I'm Buddy, your AI assistant. How can I help you today?""",
        roles=("User", "Assistant"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n",
    )
)

# Phoenix default template
register_conv_template(
    Conversation(
        name="phoenix",
        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",
        roles=("Human", "Assistant"),
        sep_style=SeparatorStyle.PHOENIX,
        sep="</s>",
    )
)

# ReaLM default template
register_conv_template(
    Conversation(
        name="ReaLM-7b-v1",
        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",
        roles=("Human", "Assistant"),
        sep_style=SeparatorStyle.PHOENIX,
        sep="</s>",
    )
)

# ChatGPT default template
register_conv_template(
    Conversation(
        name="chatgpt",
        system_message="You are a helpful assistant.",
        roles=("user", "assistant"),
        sep_style=None,
        sep=None,
    )
)

# Claude default template
register_conv_template(
    Conversation(
        name="claude",
        roles=("Human", "Assistant"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n\n",
    )
)

# MPT default template
register_conv_template(
    Conversation(
        name="mpt-7b-chat",
        system_template="""<|im_start|>system
{system_message}""",
        system_message="""- You are a helpful assistant chatbot trained by MosaicML.
- You answer questions.
- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.""",
        roles=("<|im_start|>user", "<|im_start|>assistant"),
        sep_style=SeparatorStyle.CHATML,
        sep="<|im_end|>",
        stop_token_ids=[50278, 0],
    )
)

# MPT-30b-chat default template
register_conv_template(
    Conversation(
        name="mpt-30b-chat",
        system_template="""<|im_start|>system
{system_message}""",
        system_message="""A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
        roles=("<|im_start|>user", "<|im_start|>assistant"),
        sep_style=SeparatorStyle.CHATML,
        sep="<|im_end|>",
        stop_token_ids=[50278, 0],
    )
)

# MPT-30b-instruct default template
# reference: https://huggingface.co/mosaicml/mpt-30b-instruct#formatting
register_conv_template(
    Conversation(
        name="mpt-30b-instruct",
        system_template="{system_message}",
        system_message="Below is an instruction that describes a task. Write a response that appropriately completes the request.",
        roles=("### Instruction", "### Response"),
        sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
        sep="\n\n",
        stop_token_ids=[50278, 0],
    )
)

# Bard default template
# Reference: https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L150
#            https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L40
register_conv_template(
    Conversation(
        name="bard",
        roles=("0", "1"),
        sep_style=None,
        sep=None,
    )
)

# BiLLa default template
register_conv_template(
    Conversation(
        name="billa",
        roles=("Human", "Assistant"),
        sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
        sep="\n",
        stop_str="Human:",
    )
)

# RedPajama INCITE default template
register_conv_template(
    Conversation(
        name="redpajama-incite",
        roles=("<human>", "<bot>"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n",
        stop_str="<human>",
    )
)

# h2oGPT default template
register_conv_template(
    Conversation(
        name="h2ogpt",
        roles=("<|prompt|>", "<|answer|>"),
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="</s>",
    )
)

# Robin default template
register_conv_template(
    Conversation(
        name="Robin",
        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.",
        roles=("###Human", "###Assistant"),
        sep_style=SeparatorStyle.ROBIN,
        sep="\n",
        stop_token_ids=[2, 396],
        stop_str="###",
    )
)

# Snoozy default template
# Reference: https://github.com/nomic-ai/gpt4all/blob/d4861030b778da6db59d21d2927a4aba4f9f1f43/gpt4all-bindings/python/gpt4all/gpt4all.py#L232
register_conv_template(
    Conversation(
        name="snoozy",
        system_template="### Instruction:\n{system_message}",
        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.",
        roles=("### Prompt", "### Response"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n",
        stop_str="###",
    )
)

# manticore default template
register_conv_template(
    Conversation(
        name="manticore",
        roles=("USER", "ASSISTANT"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep="\n",
        sep2="</s>",
    )
)

# Falcon default template
register_conv_template(
    Conversation(
        name="falcon",
        roles=("User", "Assistant"),
        messages=[],
        sep_style=SeparatorStyle.RWKV,
        sep="\n",
        sep2="<|endoftext|>",
        stop_str="\nUser",  # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
        stop_token_ids=[
            0,
            1,
            2,
            3,
            4,
            5,
            6,
            7,
            8,
            9,
            10,
            11,
        ],  # it better only put special tokens here, because tokenizer only remove special tokens
    )
)

# ChagGPT default template
register_conv_template(
    Conversation(
        name="polyglot_changgpt",
        roles=("B", "A"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n",
    )
)

# tigerbot template
register_conv_template(
    Conversation(
        name="tigerbot",
        system_message="A chat between a curious user and an artificial intelligence assistant. "
        "The assistant gives helpful, detailed, and polite answers to the user's questions.",
        roles=("### Instruction", "### Response"),
        sep_style=SeparatorStyle.ROBIN,
        sep="\n\n",
        stop_str="###",
    )
)

# ref: https://huggingface.co/Salesforce/xgen-7b-8k-inst
register_conv_template(
    Conversation(
        name="xgen",
        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",
        roles=("### Human: ", "###"),
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="\n",
        stop_token_ids=[50256, 0, 1, 2],
        stop_str="<|endoftext|>",
    )
)

# Internlm-chat template
register_conv_template(
    Conversation(
        name="internlm-chat",
        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",
        roles=("<|User|>", "<|Bot|>"),
        sep_style=SeparatorStyle.CHATINTERN,
        sep="<eoh>",
        sep2="<eoa>",
        stop_token_ids=[1, 103028],
        stop_str="<|User|>",
    )
)

# StarChat template
# reference: https://huggingface.co/spaces/HuggingFaceH4/starchat-playground/blob/main/dialogues.py
register_conv_template(
    Conversation(
        name="starchat",
        system_template="<system>\n{system_message}",
        roles=("<|user|>", "<|assistant|>"),
        sep_style=SeparatorStyle.CHATML,
        sep="<|end|>",
        stop_token_ids=[0, 49155],
        stop_str="<|end|>",
    )
)

# Baichuan-13B-Chat template
register_conv_template(
    # source: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/19ef51ba5bad8935b03acd20ff04a269210983bc/modeling_baichuan.py#L555
    # https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/main/generation_config.json
    # https://github.com/baichuan-inc/Baichuan-13B/issues/25
    Conversation(
        name="baichuan-chat",
        roles=("<reserved_102>", "<reserved_103>"),
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="",
        stop_token_ids=[],
    )
)

# llama2 template
# reference: https://huggingface.co/blog/codellama#conversational-instructions
# reference: https://github.com/facebookresearch/llama/blob/1a240688810f8036049e8da36b073f63d2ac552c/llama/generation.py#L212
register_conv_template(
    Conversation(
        name="llama-2",
        system_template="[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n",
        roles=("[INST]", "[/INST]"),
        sep_style=SeparatorStyle.LLAMA2,
        sep=" ",
        sep2=" </s><s>",
    )
)

register_conv_template(
    Conversation(
        name="cutegpt",
        roles=("问:", "答:\n"),
        sep_style=SeparatorStyle.NO_COLON_TWO,
        sep="\n",
        sep2="\n",
        stop_str="<end>",
    )
)

# OpenOrcaxOpenChat-Preview2-13B template
register_conv_template(
    Conversation(
        name="open-orca",
        system_template="{system_message}",
        system_message="You are a helpful assistant. Please answer truthfully and write out your "
        "thinking step by step to be sure you get the right answer. If you make a mistake or encounter "
        "an error in your thinking, say so out loud and attempt to correct it. If you don't know or "
        "aren't sure about something, say so clearly. You will act as a professional logician, mathematician, "
        "and physicist. You will also act as the most appropriate type of expert to answer any particular "
        "question or solve the relevant problem; state which expert type your are, if so. Also think of "
        "any particular named expert that would be ideal to answer the relevant question or solve the "
        "relevant problem; name and act as them, if appropriate.",
        roles=("User", "Assistant"),
        sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
        sep="<|end_of_turn|>\n",
        stop_token_ids=[32000, 32001],  # "<|end_of_turn|>"
        stop_str="User",
    )
)


# Qwen-chat default template
# source: https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/qwen_generation_utils.py#L130
register_conv_template(
    Conversation(
        name="qwen-7b-chat",
        system_template="<|im_start|>system\n{system_message}",
        system_message="You are a helpful assistant.",
        roles=("<|im_start|>user", "<|im_start|>assistant"),
        sep_style=SeparatorStyle.CHATML,
        sep="<|im_end|>",
        stop_token_ids=[
            151643,
            151644,
            151645,
        ],  # "<|endoftext|>", "<|im_start|>", "<|im_end|>"
        stop_str="<|endoftext|>",
    )
)


# AquilaChat default template
# source: https://github.com/FlagAI-Open/FlagAI/blob/master/examples/Aquila/Aquila-chat/cyg_conversation.py
register_conv_template(
    Conversation(
        name="aquila-chat",
        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.",
        roles=("Human", "Assistant", "System"),
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="###",
        sep2="",
        stop_str=["###", "</s>", "[UNK]"],
    )
)

# Llama2-Chinese default template
# source: https://huggingface.co/FlagAlpha
register_conv_template(
    Conversation(
        name="llama2-chinese",
        system_template="<s>{system_message}</s>",
        roles=("Human", "Assistant", "System"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep="\n",
        sep2="\n</s><s>",
        stop_str="</s>",
    )
)

# Vigogne Chat default template
# source: https://github.com/bofenghuang/vigogne
register_conv_template(
    Conversation(
        name="vigogne-chat",
        system_template="<|system|>: {system_message}",
        system_message="Vous êtes l'assistant IA nommé Vigogne, créé par Zaion Lab (https://zaion.ai). "
        "Vous suivez extrêmement bien les instructions. Aidez autant que vous le pouvez.",
        roles=("<|user|>", "<|assistant|>"),
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep="\n",
        sep2="</s>\n",
        stop_str="<|user|>",
    )
)

# neuralchat-v2 template
register_conv_template(
    Conversation(
        name="neural-chat-7b-v2",
        system_message="""### System:
    - You are a helpful assistant chatbot trained by Intel.
    - You answer questions.
    - You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
    - You are more than just an information source, you are also able to write poetry, short stories, and make jokes.</s>\n""",
        roles=("### User:", "### Assistant:"),
        sep_style=SeparatorStyle.NO_COLON_TWO,
        sep="\n",
        sep2="</s>",
    )
)

# neuralchat-v1.1 prompt template
register_conv_template(
    Conversation(
        name="neural-chat-7b-v1-1",
        system_template="""<|im_start|>system
{system_message}""",
        system_message="""- You are a helpful assistant chatbot trained by Intel.
- You answer questions.
- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.""",
        roles=("<|im_start|>user", "<|im_start|>assistant"),
        sep_style=SeparatorStyle.CHATML,
        sep="<|im_end|>",
        stop_token_ids=[50278, 0],
    )
)

def compute_skip_echo_len(model_name, conv, prompt):
    model_name = model_name.lower()
    if "chatglm" in model_name:
        skip_echo_len = len(conv.messages[-2][1]) + 1
    elif "dolly-v2" in model_name:
        special_toks = ["### Instruction:", "### Response:", "### End"]
        skip_echo_len = len(prompt)
        for tok in special_toks:
            skip_echo_len -= prompt.count(tok) * len(tok)
    elif "oasst" in model_name and "pythia" in model_name:
        special_toks = ["<|prompter|>", "<|assistant|>", "<|endoftext|>"]
        skip_echo_len = len(prompt)
        for tok in special_toks:
            skip_echo_len -= prompt.count(tok) * len(tok)
    elif "stablelm" in model_name:
        special_toks = ["<|SYSTEM|>", "<|USER|>", "<|ASSISTANT|>"]
        skip_echo_len = len(prompt)
        for tok in special_toks:
            skip_echo_len -= prompt.count(tok) * len(tok)
    elif "baize" in model_name:
        skip_echo_len = len(prompt)
    elif "mpt" in model_name:
        special_toks = ["<|im_start|>", "<|im_end|>"]
        skip_echo_len = len(prompt)
        for tok in special_toks:
            skip_echo_len -= prompt.count(tok) * len(tok)
    elif "llama-2" in model_name:
        skip_echo_len = len(prompt) + 1 - prompt.count("</s><s>") * 6
    elif "neural-chat" in model_name:
        skip_echo_len = len(prompt) + 1
    else:
        skip_echo_len = len(prompt) + 1 - prompt.count("</s>") * 3
    return skip_echo_len

if __name__ == "__main__":
    print("Vicuna template:")
    conv = get_conv_template("vicuna_v1.1")
    conv.append_message(conv.roles[0], "Hello!")
    conv.append_message(conv.roles[1], "Hi!")
    conv.append_message(conv.roles[0], "How are you?")
    conv.append_message(conv.roles[1], None)
    print(conv.get_prompt())

    print("\n")

    print("Llama-2 template:")
    conv = get_conv_template("llama-2")
    conv.set_system_message("You are a helpful, respectful and honest assistant.")
    conv.append_message(conv.roles[0], "Hello!")
    conv.append_message(conv.roles[1], "Hi!")
    conv.append_message(conv.roles[0], "How are you?")
    conv.append_message(conv.roles[1], None)
    print(conv.get_prompt())