-
Notifications
You must be signed in to change notification settings - Fork 4
/
openapi.json
1755 lines (1755 loc) · 55.5 KB
/
openapi.json
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
{
"components": {
"schemas": {
"ChatCompletionChoice": {
"description": "A single chat completion choice. A response will contain one or\nmore of these based on the setting of `n`.",
"properties": {
"finish_reason": {
"anyOf": [
{
"$ref": "#/components/schemas/FinishReason"
},
{
"type": "null"
}
],
"description": "The reason the response finished."
},
"index": {
"description": "A unique identifier for the completion.",
"title": "Index",
"type": "integer"
},
"logprobs": {
"anyOf": [
{
"$ref": "#/components/schemas/Logprobs"
},
{
"type": "null"
}
],
"description": "Number of log probabilities to return per output token."
},
"message": {
"allOf": [
{
"$ref": "#/components/schemas/ChatMessage"
}
],
"description": "A chat completion message generated by the model."
}
},
"required": [
"index",
"message"
],
"title": "ChatCompletionChoice",
"type": "object"
},
"ChatCompletionChunk": {
"description": "Represents a single chunk of a streaming chat completion response.\n\nThis object's schema is compatible with OpenAI's Chat Completion API.",
"examples": [
{
"choices": [],
"created": 11,
"id": "chat-cmpl-123",
"model": "my_model"
}
],
"properties": {
"choices": {
"description": "A list of chat completion choices.Can be more than one if n is greater than 1.",
"items": {
"$ref": "#/components/schemas/ChatCompletionChunkChoice"
},
"title": "Choices",
"type": "array"
},
"created": {
"description": "The Unix timestamp (in seconds) of when the chat completion was created.",
"examples": [
1672342342
],
"title": "Created",
"type": "integer"
},
"id": {
"description": "A unique identifier for the entire chat completion request. Each chunk in the stream has the same ID.",
"title": "ID",
"type": "string"
},
"model": {
"description": "The model used for the chat completion.",
"title": "Model",
"type": "string"
},
"object": {
"const": "chat.completion.chunk",
"default": "chat.completion.chunk",
"description": "Object type field which is a constant and preset.",
"enum": [
"chat.completion.chunk"
],
"title": "Object",
"type": "string"
},
"usage": {
"anyOf": [
{
"$ref": "#/components/schemas/UsageStats"
},
{
"type": "null"
}
]
}
},
"required": [
"id",
"created",
"model",
"choices"
],
"title": "ChatCompletionChunk",
"type": "object"
},
"ChatCompletionChunkChoice": {
"description": "An OpenAPI compatible schema for a chat completion chunk choice.",
"properties": {
"delta": {
"allOf": [
{
"$ref": "#/components/schemas/ChatCompletionDelta"
}
],
"description": "The generated response delta."
},
"finish_reason": {
"anyOf": [
{
"$ref": "#/components/schemas/FinishReason"
},
{
"type": "null"
}
],
"description": "The reason the response finished."
},
"index": {
"description": "A unique identifier for the completion.",
"title": "Index",
"type": "integer"
},
"logprobs": {
"anyOf": [
{
"$ref": "#/components/schemas/Logprobs"
},
{
"type": "null"
}
],
"description": "Number of log probabilities to return per output token."
}
},
"required": [
"index",
"delta"
],
"title": "ChatCompletionChunkChoice",
"type": "object"
},
"ChatCompletionDelta": {
"description": "An OpenAPI compatible schema for a chat completion choice delta.",
"properties": {
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The response content.",
"title": "Content"
},
"role": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The generated response role.",
"title": "Role"
},
"tool_calls": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/ChatCompletionDeltaToolCall"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The tool calls generated by the model, such as function calls.",
"title": "Tool Calls"
}
},
"title": "ChatCompletionDelta",
"type": "object"
},
"ChatCompletionDeltaToolCall": {
"description": "A single delta representing one partial piece of a tool call.\n\nToday this only supports function calls, but the schema supports\nindirection for different tool calls in the future.",
"properties": {
"function": {
"anyOf": [
{
"$ref": "#/components/schemas/ChatCompletionDeltaToolCallFunction"
},
{
"type": "null"
}
],
"description": "The delta of the function call generated by the model."
},
"id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the tool call.",
"title": "Id"
},
"index": {
"description": "The sequence index of the tool call.",
"title": "Index",
"type": "integer"
},
"type": {
"anyOf": [
{
"const": "function",
"enum": [
"function"
],
"type": "string"
},
{
"type": "null"
}
],
"default": "function",
"description": "The type of tool. Today only `function` is supported.",
"title": "Type"
}
},
"required": [
"index"
],
"title": "ChatCompletionDeltaToolCall",
"type": "object"
},
"ChatCompletionDeltaToolCallFunction": {
"description": "A single delta representing one partial piece of a \"function\" tool call.\n\nIt can contain part of the arguments, the name of the function, or both.",
"properties": {
"arguments": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "A partial chunk of the arguments to call the function with.",
"title": "Arguments"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "A partial chunk of the function name to call.",
"title": "Name"
}
},
"title": "ChatCompletionDeltaToolCallFunction",
"type": "object"
},
"ChatCompletionResponse": {
"description": "An OpenAI API compatible schema for a chat completion response object.",
"examples": [
{
"choices": [],
"created": 11,
"id": "chat-cmpl-123",
"model": "my_model",
"usage": {
"completion_tokens": 20,
"prompt_tokens": 10,
"total_tokens": 30
}
}
],
"properties": {
"choices": {
"description": "A list of chat completion choices.Can be more than one if n is greater than 1.",
"items": {
"$ref": "#/components/schemas/ChatCompletionChoice"
},
"title": "Choices",
"type": "array"
},
"created": {
"description": "The Unix timestamp (in seconds) of when the chat completion was created.",
"examples": [
1672342342
],
"title": "Created",
"type": "integer"
},
"id": {
"description": "A unique identifier for the chat completion.",
"title": "Id",
"type": "string"
},
"model": {
"description": "The model used for the chat completion.",
"title": "Model",
"type": "string"
},
"object": {
"const": "chat.completion",
"default": "chat.completion",
"description": "Object type field which is a constant and preset.",
"enum": [
"chat.completion"
],
"title": "Object",
"type": "string"
},
"usage": {
"allOf": [
{
"$ref": "#/components/schemas/UsageStats"
}
],
"description": "Usage statistics for the request."
}
},
"required": [
"id",
"created",
"model",
"choices",
"usage"
],
"title": "ChatCompletionResponse",
"type": "object"
},
"ChatCompletionResponseFormat": {
"description": "OctoAI chat completion response format.",
"properties": {
"schema": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The schema for the response format.",
"title": "Schema"
},
"type": {
"description": "The type of response format.",
"title": "Type",
"type": "string"
}
},
"required": [
"type"
],
"title": "ChatCompletionResponseFormat",
"type": "object"
},
"ChatMessage": {
"description": "An OpenAI API compatible schema for a single ChatMessage.",
"properties": {
"content": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"discriminator": {
"mapping": {
"image_url": "#/components/schemas/MultiModalImageMessage",
"text": "#/components/schemas/MultiModalTextMessage"
},
"propertyName": "type"
},
"oneOf": [
{
"$ref": "#/components/schemas/MultiModalImageMessage"
},
{
"$ref": "#/components/schemas/MultiModalTextMessage"
}
]
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The contents of the message.",
"title": "Content"
},
"role": {
"description": "The role of the author of this message.",
"title": "Role",
"type": "string"
},
"tool_calls": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/ToolCall"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The tool calls generated by the model, such as function calls.",
"title": "Tool Calls"
}
},
"required": [
"role",
"content"
],
"title": "ChatMessage",
"type": "object"
},
"CompletionChoice": {
"description": "Completion choice for completion requests.",
"properties": {
"finish_reason": {
"anyOf": [
{
"$ref": "#/components/schemas/FinishReason"
},
{
"type": "null"
}
],
"description": "The reason the response finished."
},
"index": {
"description": "A unique identifier for the completion.",
"title": "Index",
"type": "integer"
},
"logprobs": {
"anyOf": [
{
"$ref": "#/components/schemas/Logprobs"
},
{
"type": "null"
}
],
"description": "Number of log probabilities to return per output token."
},
"text": {
"description": "The generated text in completion response.",
"title": "Text",
"type": "string"
}
},
"required": [
"index",
"text"
],
"title": "CompletionChoice",
"type": "object"
},
"CompletionResponse": {
"description": "Represents a completion response from the API.\nNote: both the streamed and non-streamed response objects\nshare the same shape (unlike the chat endpoint).",
"examples": [
{
"choices": [],
"created": 11,
"id": "cmpl-123",
"model": "my_model",
"system_fingerprint": "system_fingerprint"
}
],
"properties": {
"choices": {
"description": "A list of completion choices.",
"items": {
"$ref": "#/components/schemas/CompletionChoice"
},
"title": "Choices",
"type": "array"
},
"created": {
"description": "The Unix timestamp (in seconds) of when the completion was created.",
"examples": [
1672342342
],
"title": "Created",
"type": "integer"
},
"id": {
"description": "A unique identifier for the completion.",
"title": "Id",
"type": "string"
},
"model": {
"description": "The model used for the completion.",
"title": "Model",
"type": "string"
},
"object": {
"const": "text_completion",
"default": "text_completion",
"description": "Object type field which is a constant and preset.",
"enum": [
"text_completion"
],
"title": "Object",
"type": "string"
},
"system_fingerprint": {
"description": "The system response fingerprint.",
"title": "System Fingerprint",
"type": "string"
},
"usage": {
"anyOf": [
{
"$ref": "#/components/schemas/UsageStats"
},
{
"type": "null"
}
],
"description": "Usage statistics for the request."
}
},
"required": [
"id",
"choices",
"created",
"model",
"system_fingerprint"
],
"title": "CompletionResponse",
"type": "object"
},
"CreateChatCompletionRequest": {
"description": "An OpenAI API compatible chat completion request.",
"examples": [
{
"max_tokens": 128,
"messages": [
{
"content": "You are a helpful assistant. Keep your responses limited to one short paragraph if possible.",
"role": "system"
},
{
"content": "Hello world",
"role": "user"
}
],
"model": "llama-2-13b-chat-fp16",
"temperature": 0.1,
"top_p": 0.9
}
],
"properties": {
"frequency_penalty": {
"default": 0.0,
"description": "Penalizes new tokens based on their frequency in the generated text so far.",
"maximum": 2.0,
"minimum": -2.0,
"title": "Frequency Penalty",
"type": "number"
},
"ignore_eos": {
"default": false,
"description": "Whether to ignore the EOS token and continue generating tokens after the EOS token is generated.",
"title": "Ignore Eos",
"type": "boolean"
},
"log_prompt": {
"default": false,
"description": "OctoAI stores request prompt if True.",
"title": "Log Prompt",
"type": "boolean"
},
"logit_bias": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"description": "Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {'50256': -100} to prevent the <|endoftext|> token from being generated.",
"title": "Logit Bias"
},
"loglikelihood": {
"default": false,
"description": "Return log probabilities for all prompt tokens excluding the first one from prefill step if True.",
"title": "Loglikelihood",
"type": "boolean"
},
"logprobs": {
"default": false,
"description": "Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.",
"title": "Logprobs",
"type": "boolean"
},
"max_tokens": {
"default": 512,
"description": "Maximum number of tokens to generate per output sequence.",
"minimum": 1.0,
"title": "Max Tokens",
"type": "integer"
},
"messages": {
"description": "A list of messages comprising the conversation so far.",
"items": {
"$ref": "#/components/schemas/ChatMessage"
},
"title": "Messages",
"type": "array"
},
"min_p": {
"default": 0.0,
"description": "Sets a dynamic threshold of the top tokens to consider based on the probability value of the most likely next token. Following https://arxiv.org/abs/2407.01082.",
"maximum": 1.0,
"minimum": 0.0,
"title": "Min P",
"type": "number"
},
"model": {
"description": "The identifier of the model to use. Can be a shared tenancy or custom model identifier.",
"title": "Model",
"type": "string"
},
"n": {
"default": 1,
"description": "Number of output sequences to return.",
"minimum": 1.0,
"title": "N",
"type": "integer"
},
"peft": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Parameter-efficient fine-tuning ID.",
"examples": [
"example_peft_id"
],
"title": "PEFT"
},
"presence_penalty": {
"default": 0.0,
"description": "Penalizes new tokens based on whether they appear in the generated text so far.",
"maximum": 2.0,
"minimum": -2.0,
"title": "Presence Penalty",
"type": "number"
},
"repetition_penalty": {
"default": 1.0,
"description": "Controls the likelihood of the model generating repeated texts.",
"exclusiveMinimum": 0.0,
"title": "Repetition Penalty",
"type": "number"
},
"response_format": {
"anyOf": [
{
"$ref": "#/components/schemas/ChatCompletionResponseFormat"
},
{
"type": "null"
}
],
"description": "Allows specification of a response format and associated schema that will constrain the LLM output to that structure. For example, using the `json_object` type allows you to provide a desired json schema for the output to follow."
},
"stop": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Generation stop condition.",
"title": "Stop"
},
"stream": {
"default": false,
"description": "If set, tokens will be streamed incrementally to users. One or more tokens will be sent as server-sent events (SSE) as they become available. For more information on read above.",
"title": "Stream",
"type": "boolean"
},
"stream_options": {
"allOf": [
{
"$ref": "#/components/schemas/StreamOptions"
}
],
"description": "If set, usageStats will be streamed on the last content-containing chunk."
},
"temperature": {
"default": 1.0,
"description": "Controls the randomness of the sampling.",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"type": "number"
},
"tool_choice": {
"anyOf": [
{
"const": "auto",
"enum": [
"auto"
],
"type": "string"
},
{
"const": "required",
"enum": [
"required"
],
"type": "string"
},
{
"$ref": "#/components/schemas/FunctionChoice"
},
{
"type": "null"
}
],
"default": "auto",
"description": "Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.",
"title": "Tool Choice"
},
"tools": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/ToolDefinition"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.",
"title": "Tools"
},
"top_logprobs": {
"default": 0,
"description": "An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used.",
"title": "Top Logprobs",
"type": "integer"
},
"top_p": {
"default": 1.0,
"description": "Controls the cumulative probability of the top tokens to consider.",
"exclusiveMinimum": 0.0,
"maximum": 1.0,
"title": "Top P",
"type": "number"
},
"user": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "A unique identifier representing your end-user.",
"title": "User"
}
},
"required": [
"model",
"messages"
],
"title": "CreateChatCompletionRequest",
"type": "object"
},
"CreateCompletionRequest": {
"description": "`POST https://text.octoai.run/v1/completions`\n\nCompletes the provided prefix prompt given the parameters.\n\nYou can view this as the \"raw\" API to the model which provides\nmore complete user control than the chat completions API.\n\nThis API is compatible with OpenAI's API.",
"properties": {
"best_of": {
"default": 1,
"description": "Number of sequences that are generated from the prompt.`best_of` must be greater than or equal to `n`.",
"title": "Best Of",
"type": "integer"
},
"echo": {
"default": false,
"description": "Echo back the prompt in addition to the completion.",
"title": "Echo",
"type": "boolean"
},
"frequency_penalty": {
"default": 0.0,
"description": "Penalizes new tokens based on their frequency in the generated text so far.",
"maximum": 2.0,
"minimum": -2.0,
"title": "Frequency Penalty",
"type": "number"
},
"ignore_eos": {
"default": false,
"description": "Whether to ignore the EOS token and continue generating tokens after the EOS token is generated.",
"title": "Ignore Eos",
"type": "boolean"
},
"log_prompt": {
"default": false,
"description": "OctoAI stores request prompt if True.",
"title": "Log Prompt",
"type": "boolean"
},
"logit_bias": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"description": "Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {'50256': -100} to prevent the <|endoftext|> token from being generated.",
"title": "Logit Bias"
},
"loglikelihood": {
"default": false,
"description": "Return log probabilities for all prompt tokens excluding the first one from prefill step if True.",
"title": "Loglikelihood",
"type": "boolean"
},
"logprobs": {
"anyOf": [
{
"maximum": 5.0,
"minimum": 0.0,
"type": "integer"
},
{
"type": "null"
}
],
"description": "Number of log probabilities to return per output token.",
"title": "Logprobs"
},
"max_tokens": {
"default": 512,
"description": "Maximum number of tokens to generate per output sequence.",
"minimum": 1.0,
"title": "Max Tokens",
"type": "integer"
},
"min_p": {
"default": 0.0,
"description": "Sets a dynamic threshold of the top tokens to consider based on the probability value of the most likely next token. Following https://arxiv.org/abs/2407.01082.",
"maximum": 1.0,
"minimum": 0.0,
"title": "Min P",
"type": "number"
},
"model": {
"description": "The identifier of the model to use. Can be a shared tenancy or custom model identifier.",
"title": "Model",
"type": "string"
},
"n": {
"default": 1,
"description": "Number of output sequences to return.",
"minimum": 1.0,
"title": "N",
"type": "integer"
},
"peft": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Parameter-efficient fine-tuning ID.",
"examples": [
"example_peft_id"
],
"title": "PEFT"
},
"presence_penalty": {
"default": 0.0,
"description": "Penalizes new tokens based on whether they appear in the generated text so far.",
"maximum": 2.0,
"minimum": -2.0,
"title": "Presence Penalty",
"type": "number"
},
"prompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The prompt to generate completions from.",
"title": "Prompt"
},
"repetition_penalty": {
"default": 1.0,
"description": "Controls the likelihood of the model generating repeated texts.",
"exclusiveMinimum": 0.0,
"title": "Repetition Penalty",
"type": "number"
},
"seed": {
"default": 0,
"description": "If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.",
"title": "Seed",
"type": "integer"
},
"stop": {