-
Notifications
You must be signed in to change notification settings - Fork 119
/
config_template.yml
290 lines (290 loc) · 8.9 KB
/
config_template.yml
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
# {{ index .Help "model" }}
default-model: gpt-4o
# {{ index .Help "format-text" }}
format-text:
markdown: '{{ index .Config.FormatText "markdown" }}'
json: '{{ index .Config.FormatText "json" }}'
# {{ index .Help "roles" }}
roles:
"default": []
# Example, a role called `shell`:
# shell:
# - you are a shell expert
# - you do not explain anything
# - you simply output one liners to solve the problems you're asked
# - you do not provide any explanation whatsoever, ONLY the command
# {{ index .Help "format" }}
format: false
# {{ index .Help "role" }}
role: "default"
# {{ index .Help "raw" }}
raw: false
# {{ index .Help "quiet" }}
quiet: false
# {{ index .Help "temp" }}
temp: 1.0
# {{ index .Help "topp" }}
topp: 1.0
# {{ index .Help "topk" }}
topk: 50
# {{ index .Help "no-limit" }}
no-limit: false
# {{ index .Help "word-wrap" }}
word-wrap: 80
# {{ index .Help "prompt-args" }}
include-prompt-args: false
# {{ index .Help "prompt" }}
include-prompt: 0
# {{ index .Help "max-retries" }}
max-retries: 5
# {{ index .Help "fanciness" }}
fanciness: 10
# {{ index .Help "status-text" }}
status-text: Generating
# {{ index .Help "theme" }}
theme: charm
# {{ index .Help "max-input-chars" }}
max-input-chars: 12250
# {{ index .Help "max-tokens" }}
# max-tokens: 100
# {{ index .Help "apis" }}
apis:
openai:
base-url: https://api.openai.com/v1
api-key:
api-key-env: OPENAI_API_KEY
models: # https://platform.openai.com/docs/models
gpt-4o-mini:
aliases: ["4o-mini"]
max-input-chars: 392000
fallback: gpt-4o
gpt-4o:
aliases: ["4o"]
max-input-chars: 392000
fallback: gpt-4
gpt-4:
aliases: ["4"]
max-input-chars: 24500
fallback: gpt-3.5-turbo
gpt-4-1106-preview:
aliases: ["128k"]
max-input-chars: 392000
fallback: gpt-4
gpt-4-32k:
aliases: ["32k"]
max-input-chars: 98000
fallback: gpt-4
gpt-3.5-turbo:
aliases: ["35t"]
max-input-chars: 12250
fallback: gpt-3.5
gpt-3.5-turbo-1106:
aliases: ["35t-1106"]
max-input-chars: 12250
fallback: gpt-3.5-turbo
gpt-3.5-turbo-16k:
aliases: ["35t16k"]
max-input-chars: 44500
fallback: gpt-3.5
gpt-3.5:
aliases: ["35"]
max-input-chars: 12250
fallback:
copilot:
base-url: https://api.githubcopilot.com
models:
gpt-4o:
max-input-chars: 392000
anthropic:
base-url: https://api.anthropic.com/v1
api-key:
api-key-env: ANTHROPIC_API_KEY
models: # https://docs.anthropic.com/en/docs/about-claude/models
claude-3-5-sonnet-latest:
aliases: ["claude3.5-sonnet", "claude-3-5-sonnet", "sonnet-3.5"]
max-input-chars: 680000
claude-3-5-sonnet-20241022:
max-input-chars: 680000
claude-3-5-sonnet-20240620:
max-input-chars: 680000
claude-3-opus-20240229:
aliases: ["claude3-opus", "opus"]
max-input-chars: 680000
cohere:
base-url: https://api.cohere.com/v1
models:
command-r-plus:
max-input-chars: 128000
command-r:
max-input-chars: 128000
google:
models:
gemini-1.5-pro-latest:
aliases: ["gemini"]
max-input-chars: 392000
gemini-1.5-flash-latest:
aliases: ["flash"]
max-input-chars: 392000
ollama:
base-url: http://localhost:11434/api
models: # https://ollama.com/library
"llama3.2:3b":
aliases: ["llama3.2"]
max-input-chars: 650000
"llama3.2:1b":
aliases: ["llama3.2_1b"]
max-input-chars: 650000
"llama3:70b":
aliases: ["llama3"]
max-input-chars: 650000
perplexity:
base-url: https://api.perplexity.ai
api-key:
api-key-env: PERPLEXITY_API_KEY
models: # https://docs.perplexity.ai/docs/model-cards
llama-3-sonar-small-32k-chat:
aliases: ["llama3-ss"]
max-input-chars: 32768
llama-3-sonar-small-32k-online:
aliases: ["llam3-sso"]
max-input-chars: 28000
llama-3-sonar-large-32k-chat:
aliases: ["llam3-sl"]
max-input-chars: 32768
llama-3-sonar-large-32k-online:
aliases: ["llam3-slo"]
max-input-chars: 28000
llama-3-8b-instruct:
aliases: ["llam3-8bi"]
max-input-chars: 8192
llama-3-70b-instruct:
aliases: ["llam3-70bi"]
max-input-chars: 8192
groq:
base-url: https://api.groq.com/openai/v1
api-key:
api-key-env: GROQ_API_KEY
models: # https://console.groq.com/docs/models
gemma-7b-it:
aliases: ["gemma"]
max-input-chars: 24500
gemma2-9b-it:
aliases: ["gemma2"]
max-input-chars: 24500
llama3-groq-70b-8192-tool-use-preview:
aliases: ["llama3-tool"]
max-input-chars: 24500
llama3-groq-8b-8192-tool-use-preview:
aliases: ["llama3-8b-tool"]
max-input-chars: 24500
llama-3.1-70b-versatile:
aliases: ["llama3.1", "llama3.1-70b", "llama3.1-versatile"]
max-input-chars: 392000
llama-3.1-8b-instant:
aliases: ["llama3.1-8b", "llama3.1-instant"]
max-input-chars: 392000
llama-guard-3-8b:
aliases: ["llama-guard"]
max-input-chars: 24500
llama3-70b-8192:
aliases: ["llama3", "llama3-70b"]
max-input-chars: 24500
fallback: llama3-8b-8192
llama3-8b-8192:
aliases: ["llama3-8b"]
max-input-chars: 24500
mixtral-8x7b-32768:
aliases: ["mixtral"]
max-input-chars: 98000
cerebras:
base-url: https://api.cerebras.ai/v1
api-key:
api-key-env: CEREBRAS_API_KEY
models: # https://inference-docs.cerebras.ai/introduction
llama3.1-8b:
aliases: ["llama3.1-8b-cerebras"]
max-input-chars: 24500
llama3.1-70b:
aliases: ["llama3.1-cerebras", "llama3.1-70b-cerebras"]
max-input-chars: 24500
sambanova:
base-url: https://api.sambanova.ai/v1
api-key:
api-key-env: SAMBANOVA_API_KEY
models: # https://community.sambanova.ai/t/supported-models/193
Meta-Llama-3.1-8B-Instruct:
aliases: ["llama3.1-8b-sambanova-4k", "llama3.1-instruct-8b-sambanova-4k"]
max-input-chars: 12250
Meta-Llama-3.1-70B-Instruct:
aliases: ["llama3.1-70b-sambanova-4k", "llama3.1-instruct-70b-sambanova-4k"]
max-input-chars: 12250
Meta-Llama-3.1-405B-Instruct:
aliases: ["llama3.1-405b-sambanova-4k", "llama3.1-instruct-405b-sambanova-4k"]
max-input-chars: 12250
Meta-Llama-3.1-8B-Instruct-8k:
aliases: ["llama3.1-8b-sambanova", "llama3.1-instruct-8b-sambanova", "llama3.1-8b-sambanova-8k", "llama3.1-instruct-8b-sambanova-8k"]
max-input-chars: 24500
Meta-Llama-3.1-70B-Instruct-8k:
aliases: ["llama3.1-70b-sambanova", "llama3.1-instruct-70b-sambanova", "llama3.1-70b-sambanova-8k", "llama3.1-instruct-70b-sambanova-8k"]
max-input-chars: 24500
Meta-Llama-3.1-405B-Instruct-8k:
aliases: ["llama3.1-405b-sambanova", "llama3.1-instruct-405b-sambanova", "llama3.1-405b-sambanova-8k", "llama3.1-instruct-405b-sambanova-8k"]
max-input-chars: 24500
localai:
# LocalAI setup instructions: https://github.com/go-skynet/LocalAI#example-use-gpt4all-j-model
base-url: http://localhost:8080
models:
ggml-gpt4all-j:
aliases: ["local", "4all"]
max-input-chars: 12250
fallback:
azure:
# Set to 'azure-ad' to use Active Directory
# Azure OpenAI setup: https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource
base-url: https://YOUR_RESOURCE_NAME.openai.azure.com
api-key:
api-key-env: AZURE_OPENAI_KEY
models:
gpt-4:
aliases: ["az4"]
max-input-chars: 24500
fallback: gpt-35-turbo
gpt-35-turbo:
aliases: ["az35t"]
max-input-chars: 12250
fallback: gpt-35
gpt-35:
aliases: ["az35"]
max-input-chars: 12250
fallback:
runpod:
# https://docs.runpod.io/serverless/workers/vllm/openai-compatibility
base-url: https://api.runpod.ai/v2/${YOUR_ENDPOINT}/openai/v1
api-key:
api-key-env: RUNPOD_API_KEY
models:
openchat/openchat-3.5-1210:
aliases: ["openchat"]
max-input-chars: 8192
mistral:
base-url: https://api.mistral.ai/v1
api-key:
api-key-env: MISTRAL_API_KEY
models: # https://docs.mistral.ai/getting-started/models/
mistral-large-latest:
aliases: ["mistral-large"]
max-input-chars: 384000
open-mistral-nemo:
aliases: ["mistral-nemo"]
max-input-chars: 384000
deepseek:
base-url: https://api.deepseek.com/
api-key:
api-key-env: DEEPSEEK_API_KEY
models: # https://platform.deepseek.com/api-docs/api/list-models/
deepseek-chat:
aliases: ["ds-chat"]
max-input-chars: 384000
deepseek-code:
aliases: ["ds-code"]
max-input-chars: 384000