XFE Git
XFE Studio Git
Git 首页 全局搜索
XFE 主站 文档 NuGet
公开
关注 0 Fork 0 Star 1
返回提交历史

XFEstudio/gpt4free

Update (g4f/models.py g4f/Provider/airforce/AirforceChat.py docs/providers-and-models.md)

3a15957d
kqlio67 <kqlio67@users.noreply.github.com>
提交于
父提交 d2f36d5

代码差异

3 个文件 +71 -438
Modified docs/providers-and-models.md +2 -2
@@ -19,8 +19,8 @@ This document provides an overview of various AI providers and models, including
19 19 |----------|-------------|--------------|---------------|--------|--------|------|
20 20 |[ai4chat.co](https://www.ai4chat.co)|`g4f.Provider.Ai4Chat`|`gpt-4`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
21 21 |[aichatfree.info](https://aichatfree.info)|`g4f.Provider.AIChatFree`|`gemini-pro`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
22 |[api.airforce](https://api.airforce)|`g4f.Provider.AiMathGPT`|`llama-3.1-70b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
23 |[api.airforce](https://api.airforce)|`g4f.Provider.Airforce`|`claude-3-haiku, claude-3-sonnet, claude-3-opus, gpt-4, gpt-4-turbo, gpt-4o-mini, gpt-3.5-turbo, llama-3-70b, llama-3-8b, llama-2-13b, llama-3.1-405b, llama-3.1-70b, llama-3.1-8b, llamaguard-2-8b, llamaguard-7b, llama-3.2-90b, llamaguard-3-8b, llama-3.2-11b, llamaguard-3-11b, llama-3.2-3b, llama-3.2-1b, llama-2-7b, mixtral-8x7b, mixtral-8x22b, mythomax-13b, openchat-3.5, qwen-2-72b, qwen-2-5-7b, qwen-2-5-72b, gemma-2b, gemma-2-9b, gemma-2b-27b, gemini-flash, gemini-pro, dbrx-instruct, deepseek-coder, hermes-2-dpo, hermes-2, openhermes-2.5, wizardlm-2-8x22b, phi-2, solar-10-7b, cosmosrp, lfm-40b, german-7b, zephyr-7b`|`flux, flux-realism', flux-anime, flux-3d, flux-disney, flux-pixel, flux-4o, any-dark, sdxl`|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
22 |[aimathgpt.forit.ai](https://aimathgpt.forit.ai)|`g4f.Provider.AiMathGPT`|`llama-3.1-70b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
23 |[api.airforce](https://api.airforce)|`g4f.Provider.Airforce`|`gpt-4o, gpt-4o-mini, gpt-4-turbo, llama-2-7b, llama-3.1-8b, llama-3.1-70b, hermes-2-pro, hermes-2-dpo, phi-2, deepseek-coder, openchat-3.5, openhermes-2.5, cosmosrp, lfm-40b, german-7b, zephyr-7b, neural-7b`|`flux, flux-realism', flux-anime, flux-3d, flux-disney, flux-pixel, flux-4o, any-dark, sdxl`|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
24 24 |[aiuncensored.info](https://www.aiuncensored.info)|`g4f.Provider.AIUncensored`|✔|✔|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
25 25 |[allyfy.chat](https://allyfy.chat/)|`g4f.Provider.Allyfy`|`gpt-3.5-turbo`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
26 26 |[bing.com](https://bing.com/chat)|`g4f.Provider.Bing`|`gpt-4`|✔|`gpt-4-vision`|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌+✔|
Modified g4f/Provider/airforce/AirforceChat.py +27 -234
@@ -3,6 +3,7 @@ import re
3 3 from aiohttp import ClientSession
4 4 import json
5 5 from typing import List
6 import requests
6 7
7 8 from ...typing import AsyncResult, Messages
8 9 from ..base_provider import AsyncGeneratorProvider, ProviderModelMixin
@@ -51,258 +52,50 @@ class AirforceChat(AsyncGeneratorProvider, ProviderModelMixin):
51 52 supports_system_message = True
52 53 supports_message_history = True
53 54
54 default_model = 'llama-3-70b-chat'
55 text_models = [
56 # anthropic
57 'claude-3-haiku-20240307',
58 'claude-3-sonnet-20240229',
59 'claude-3-5-sonnet-20240620',
60 'claude-3-5-sonnet-20241022',
61 'claude-3-opus-20240229',
62
63 # openai
64 'chatgpt-4o-latest',
65 'gpt-4',
66 'gpt-4-turbo',
67 'gpt-4o-2024-05-13',
68 'gpt-4o-mini-2024-07-18',
69 'gpt-4o-mini',
70 'gpt-4o-2024-08-06',
71 'gpt-3.5-turbo',
72 'gpt-3.5-turbo-0125',
73 'gpt-3.5-turbo-1106',
74 'gpt-4o',
75 'gpt-4-turbo-2024-04-09',
76 'gpt-4-0125-preview',
77 'gpt-4-1106-preview',
78
79 # meta-llama
80 default_model,
81 'llama-3-70b-chat-turbo',
82 'llama-3-8b-chat',
83 'llama-3-8b-chat-turbo',
84 'llama-3-70b-chat-lite',
85 'llama-3-8b-chat-lite',
86 'llama-2-13b-chat',
87 'llama-3.1-405b-turbo',
88 'llama-3.1-70b-turbo',
89 'llama-3.1-8b-turbo',
90 'LlamaGuard-2-8b',
91 'llamaguard-7b',
92 'Llama-Vision-Free',
93 'Llama-Guard-7b',
94 'Llama-3.2-90B-Vision-Instruct-Turbo',
95 'Meta-Llama-Guard-3-8B',
96 'Llama-3.2-11B-Vision-Instruct-Turbo',
97 'Llama-Guard-3-11B-Vision-Turbo',
98 'Llama-3.2-3B-Instruct-Turbo',
99 'Llama-3.2-1B-Instruct-Turbo',
100 'llama-2-7b-chat-int8',
101 'llama-2-7b-chat-fp16',
102 'Llama 3.1 405B Instruct',
103 'Llama 3.1 70B Instruct',
104 'Llama 3.1 8B Instruct',
105
106 # mistral-ai
107 'Mixtral-8x7B-Instruct-v0.1',
108 'Mixtral-8x22B-Instruct-v0.1',
109 'Mistral-7B-Instruct-v0.1',
110 'Mistral-7B-Instruct-v0.2',
111 'Mistral-7B-Instruct-v0.3',
112
113 # Gryphe
114 'MythoMax-L2-13b-Lite',
115 'MythoMax-L2-13b',
116
117 # openchat
118 'openchat-3.5-0106',
119
120 # qwen
121 #'Qwen1.5-72B-Chat', # Empty answer
122 #'Qwen1.5-110B-Chat', # Empty answer
123 'Qwen2-72B-Instruct',
124 'Qwen2.5-7B-Instruct-Turbo',
125 'Qwen2.5-72B-Instruct-Turbo',
126
127 # google
128 'gemma-2b-it',
129 'gemma-2-9b-it',
130 'gemma-2-27b-it',
131
132 # gemini
133 'gemini-1.5-flash',
134 'gemini-1.5-pro',
135
136 # databricks
137 'dbrx-instruct',
138
139 # deepseek-ai
140 'deepseek-coder-6.7b-base',
141 'deepseek-coder-6.7b-instruct',
142 'deepseek-math-7b-instruct',
143
144 # NousResearch
145 'deepseek-math-7b-instruct',
146 'Nous-Hermes-2-Mixtral-8x7B-DPO',
147 'hermes-2-pro-mistral-7b',
148
149 # teknium
150 'openhermes-2.5-mistral-7b',
151
152 # microsoft
153 'WizardLM-2-8x22B',
154 'phi-2',
155
156 # upstage
157 'SOLAR-10.7B-Instruct-v1.0',
158
159 # pawan
160 'cosmosrp',
161
162 # liquid
163 'lfm-40b-moe',
164
165 # DiscoResearch
166 'discolm-german-7b-v1',
167
168 # tiiuae
169 'falcon-7b-instruct',
170
171 # defog
172 'sqlcoder-7b-2',
173
174 # tinyllama
175 'tinyllama-1.1b-chat',
176
177 # HuggingFaceH4
178 'zephyr-7b-beta',
179 ]
55 default_model = 'llama-3.1-70b-chat'
56 response = requests.get('https://api.airforce/models')
57 data = response.json()
58
59 text_models = [model['id'] for model in data['data']]
180 60
181 61 models = [*text_models]
182 62
183 63 model_aliases = {
184 # anthropic
185 "claude-3-haiku": "claude-3-haiku-20240307",
186 "claude-3-sonnet": "claude-3-sonnet-20240229",
187 "claude-3.5-sonnet": "claude-3-5-sonnet-20240620",
188 "claude-3.5-sonnet": "claude-3-5-sonnet-20241022",
189 "claude-3-opus": "claude-3-opus-20240229",
190
191 # openai
192 "gpt-4o": "chatgpt-4o-latest",
193 #"gpt-4": "gpt-4",
194 #"gpt-4-turbo": "gpt-4-turbo",
195 "gpt-4o": "gpt-4o-2024-05-13",
196 "gpt-4o-mini": "gpt-4o-mini-2024-07-18",
197 #"gpt-4o-mini": "gpt-4o-mini",
198 "gpt-4o": "gpt-4o-2024-08-06",
199 "gpt-3.5-turbo": "gpt-3.5-turbo",
200 "gpt-3.5-turbo": "gpt-3.5-turbo-0125",
201 "gpt-3.5-turbo": "gpt-3.5-turbo-1106",
202 #"gpt-4o": "gpt-4o",
203 "gpt-4-turbo": "gpt-4-turbo-2024-04-09",
204 "gpt-4": "gpt-4-0125-preview",
205 "gpt-4": "gpt-4-1106-preview",
206
207 # meta-llama
208 "llama-3-70b": "llama-3-70b-chat",
209 "llama-3-8b": "llama-3-8b-chat",
210 "llama-3-8b": "llama-3-8b-chat-turbo",
211 "llama-3-70b": "llama-3-70b-chat-lite",
212 "llama-3-8b": "llama-3-8b-chat-lite",
213 "llama-2-13b": "llama-2-13b-chat",
214 "llama-3.1-405b": "llama-3.1-405b-turbo",
215 "llama-3.1-70b": "llama-3.1-70b-turbo",
216 "llama-3.1-8b": "llama-3.1-8b-turbo",
217 "llamaguard-2-8b": "LlamaGuard-2-8b",
218 "llamaguard-7b": "llamaguard-7b",
219 #"llama_vision_free": "Llama-Vision-Free", # Unknown
220 "llamaguard-7b": "Llama-Guard-7b",
221 "llama-3.2-90b": "Llama-3.2-90B-Vision-Instruct-Turbo",
222 "llamaguard-3-8b": "Meta-Llama-Guard-3-8B",
223 "llama-3.2-11b": "Llama-3.2-11B-Vision-Instruct-Turbo",
224 "llamaguard-3-11b": "Llama-Guard-3-11B-Vision-Turbo",
225 "llama-3.2-3b": "Llama-3.2-3B-Instruct-Turbo",
226 "llama-3.2-1b": "Llama-3.2-1B-Instruct-Turbo",
227 "llama-2-7b": "llama-2-7b-chat-int8",
228 "llama-2-7b": "llama-2-7b-chat-fp16",
229 "llama-3.1-405b": "Llama 3.1 405B Instruct",
230 "llama-3.1-70b": "Llama 3.1 70B Instruct",
231 "llama-3.1-8b": "Llama 3.1 8B Instruct",
232
233 # mistral-ai
234 "mixtral-8x7b": "Mixtral-8x7B-Instruct-v0.1",
235 "mixtral-8x22b": "Mixtral-8x22B-Instruct-v0.1",
236 "mixtral-8x7b": "Mistral-7B-Instruct-v0.1",
237 "mixtral-8x7b": "Mistral-7B-Instruct-v0.2",
238 "mixtral-8x7b": "Mistral-7B-Instruct-v0.3",
239
240 # Gryphe
241 "mythomax-13b": "MythoMax-L2-13b-Lite",
242 "mythomax-13b": "MythoMax-L2-13b",
243
244 64 # openchat
245 65 "openchat-3.5": "openchat-3.5-0106",
246
247 # qwen
248 #"qwen-1.5-72b": "Qwen1.5-72B-Chat", # Empty answer
249 #"qwen-1.5-110b": "Qwen1.5-110B-Chat", # Empty answer
250 "qwen-2-72b": "Qwen2-72B-Instruct",
251 "qwen-2-5-7b": "Qwen2.5-7B-Instruct-Turbo",
252 "qwen-2-5-72b": "Qwen2.5-72B-Instruct-Turbo",
253
254 # google
255 "gemma-2b": "gemma-2b-it",
256 "gemma-2-9b": "gemma-2-9b-it",
257 "gemma-2b-27b": "gemma-2-27b-it",
258
259 # gemini
260 "gemini-flash": "gemini-1.5-flash",
261 "gemini-pro": "gemini-1.5-pro",
262
263 # databricks
264 "dbrx-instruct": "dbrx-instruct",
265
66
266 67 # deepseek-ai
267 #"deepseek-coder": "deepseek-coder-6.7b-base",
268 68 "deepseek-coder": "deepseek-coder-6.7b-instruct",
269 #"deepseek-math": "deepseek-math-7b-instruct",
270
69
271 70 # NousResearch
272 #"deepseek-math": "deepseek-math-7b-instruct",
273 71 "hermes-2-dpo": "Nous-Hermes-2-Mixtral-8x7B-DPO",
274 "hermes-2": "hermes-2-pro-mistral-7b",
275
72 "hermes-2-pro": "hermes-2-pro-mistral-7b",
73
276 74 # teknium
277 75 "openhermes-2.5": "openhermes-2.5-mistral-7b",
278
279 # microsoft
280 "wizardlm-2-8x22b": "WizardLM-2-8x22B",
281 #"phi-2": "phi-2",
282
283 # upstage
284 "solar-10-7b": "SOLAR-10.7B-Instruct-v1.0",
285
286 # pawan
287 #"cosmosrp": "cosmosrp",
288
76
289 77 # liquid
290 78 "lfm-40b": "lfm-40b-moe",
291
79
292 80 # DiscoResearch
293 81 "german-7b": "discolm-german-7b-v1",
294
295 # tiiuae
296 #"falcon-7b": "falcon-7b-instruct",
297
298 # defog
299 #"sqlcoder-7b": "sqlcoder-7b-2",
300
301 # tinyllama
302 #"tinyllama-1b": "tinyllama-1.1b-chat",
303
82
83 # meta-llama
84 "llama-2-7b": "llama-2-7b-chat-int8",
85 "llama-2-7b": "llama-2-7b-chat-fp16",
86 "llama-3.1-70b": "llama-3.1-70b-chat",
87 "llama-3.1-8b": "llama-3.1-8b-chat",
88 "llama-3.1-70b": "llama-3.1-70b-turbo",
89 "llama-3.1-8b": "llama-3.1-8b-turbo",
90
91 # inferless
92 "neural-7b": "neural-chat-7b-v3-1",
93
304 94 # HuggingFaceH4
305 95 "zephyr-7b": "zephyr-7b-beta",
96
97 # llmplayground.net
98 #"any-uncensored": "any-uncensored",
306 99 }
307 100
308 101 @classmethod
Modified g4f/models.py +42 -202
@@ -98,32 +98,32 @@ default = Model(
98 98 gpt_35_turbo = Model(
99 99 name = 'gpt-3.5-turbo',
100 100 base_provider = 'OpenAI',
101 best_provider = IterListProvider([DarkAI, Airforce, Liaobots, Allyfy])
101 best_provider = IterListProvider([DarkAI, Liaobots, Allyfy])
102 102 )
103 103
104 104 # gpt-4
105 105 gpt_4o = Model(
106 106 name = 'gpt-4o',
107 107 base_provider = 'OpenAI',
108 best_provider = IterListProvider([Blackbox, ChatGptEs, DarkAI, Airforce, ChatGpt, Liaobots, OpenaiChat])
108 best_provider = IterListProvider([Blackbox, ChatGptEs, DarkAI, ChatGpt, Airforce, Liaobots, OpenaiChat])
109 109 )
110 110
111 111 gpt_4o_mini = Model(
112 112 name = 'gpt-4o-mini',
113 113 base_provider = 'OpenAI',
114 best_provider = IterListProvider([DDG, ChatGptEs, FreeNetfly, Pizzagpt, MagickPen, RubiksAI, Liaobots, ChatGpt, Airforce, OpenaiChat])
114 best_provider = IterListProvider([DDG, ChatGptEs, FreeNetfly, Pizzagpt, MagickPen, ChatGpt, Airforce, RubiksAI, Liaobots, OpenaiChat])
115 115 )
116 116
117 117 gpt_4_turbo = Model(
118 118 name = 'gpt-4-turbo',
119 119 base_provider = 'OpenAI',
120 best_provider = IterListProvider([Liaobots, Airforce, ChatGpt, Bing])
120 best_provider = IterListProvider([ChatGpt, Airforce, Liaobots, Bing])
121 121 )
122 122
123 123 gpt_4 = Model(
124 124 name = 'gpt-4',
125 125 base_provider = 'OpenAI',
126 best_provider = IterListProvider([Chatgpt4Online, Ai4Chat, ChatGpt, Airforce, Bing, OpenaiChat, gpt_4_turbo.best_provider, gpt_4o.best_provider, gpt_4o_mini.best_provider])
126 best_provider = IterListProvider([Chatgpt4Online, ChatGpt, Bing, OpenaiChat, gpt_4_turbo.best_provider, gpt_4o.best_provider, gpt_4o_mini.best_provider])
127 127 )
128 128
129 129 # o1
@@ -161,24 +161,17 @@ llama_2_7b = Model(
161 161 base_provider = "Meta Llama",
162 162 best_provider = IterListProvider([Cloudflare, Airforce])
163 163 )
164
165 llama_2_13b = Model(
166 name = "llama-2-13b",
167 base_provider = "Meta Llama",
168 best_provider = Airforce
169 )
170
171 164 # llama 3
172 165 llama_3_8b = Model(
173 166 name = "llama-3-8b",
174 167 base_provider = "Meta Llama",
175 best_provider = IterListProvider([Cloudflare, Airforce])
168 best_provider = IterListProvider([Cloudflare])
176 169 )
177 170
178 171 llama_3_70b = Model(
179 172 name = "llama-3-70b",
180 173 base_provider = "Meta Llama",
181 best_provider = IterListProvider([ReplicateHome, Airforce])
174 best_provider = IterListProvider([ReplicateHome])
182 175 )
183 176
184 177 # llama 3.1
@@ -191,84 +184,39 @@ llama_3_1_8b = Model(
191 184 llama_3_1_70b = Model(
192 185 name = "llama-3.1-70b",
193 186 base_provider = "Meta Llama",
194 best_provider = IterListProvider([DDG, DeepInfraChat, Blackbox, TeachAnything, DarkAI, AiMathGPT, RubiksAI, Airforce, HuggingChat, HuggingFace, PerplexityLabs])
187 best_provider = IterListProvider([DDG, DeepInfraChat, Blackbox, TeachAnything, DarkAI, AiMathGPT, Airforce, RubiksAI, HuggingChat, HuggingFace, PerplexityLabs])
195 188 )
196 189
197 190 llama_3_1_405b = Model(
198 191 name = "llama-3.1-405b",
199 192 base_provider = "Meta Llama",
200 best_provider = IterListProvider([Blackbox, DarkAI, Airforce])
193 best_provider = IterListProvider([Blackbox, DarkAI])
201 194 )
202 195
203 196 # llama 3.2
204 197 llama_3_2_1b = Model(
205 198 name = "llama-3.2-1b",
206 199 base_provider = "Meta Llama",
207 best_provider = IterListProvider([Cloudflare, Airforce])
208 )
209
210 llama_3_2_3b = Model(
211 name = "llama-3.2-3b",
212 base_provider = "Meta Llama",
213 best_provider = IterListProvider([Airforce])
200 best_provider = IterListProvider([Cloudflare])
214 201 )
215 202
216 203 llama_3_2_11b = Model(
217 204 name = "llama-3.2-11b",
218 205 base_provider = "Meta Llama",
219 best_provider = IterListProvider([HuggingChat, Airforce, HuggingFace])
220 )
221
222 llama_3_2_90b = Model(
223 name = "llama-3.2-90b",
224 base_provider = "Meta Llama",
225 best_provider = IterListProvider([Airforce])
226 )
227
228
229 # llamaguard
230 llamaguard_7b = Model(
231 name = "llamaguard-7b",
232 base_provider = "Meta Llama",
233 best_provider = Airforce
234 )
235
236 llamaguard_2_8b = Model(
237 name = "llamaguard-2-8b",
238 base_provider = "Meta Llama",
239 best_provider = Airforce
240 )
241
242 llamaguard_3_8b = Model(
243 name = "llamaguard-3-8b",
244 base_provider = "Meta Llama",
245 best_provider = Airforce
246 )
247
248 llamaguard_3_11b = Model(
249 name = "llamaguard-3-11b",
250 base_provider = "Meta Llama",
251 best_provider = Airforce
206 best_provider = IterListProvider([HuggingChat, HuggingFace])
252 207 )
253 208
254
255 209 ### Mistral ###
256 210 mistral_7b = Model(
257 211 name = "mistral-7b",
258 212 base_provider = "Mistral",
259 best_provider = IterListProvider([Free2GPT, Airforce])
213 best_provider = IterListProvider([Free2GPT])
260 214 )
261 215
262 216 mixtral_8x7b = Model(
263 217 name = "mixtral-8x7b",
264 218 base_provider = "Mistral",
265 best_provider = IterListProvider([DDG, ReplicateHome, Airforce])
266 )
267
268 mixtral_8x22b = Model(
269 name = "mixtral-8x22b",
270 base_provider = "Mistral",
271 best_provider = IterListProvider([Airforce])
219 best_provider = IterListProvider([DDG, ReplicateHome])
272 220 )
273 221
274 222 mistral_nemo = Model(
@@ -279,8 +227,8 @@ mistral_nemo = Model(
279 227
280 228
281 229 ### NousResearch ###
282 hermes_2 = Model(
283 name = "hermes-2",
230 hermes_2_pro = Model(
231 name = "hermes-2-pro",
284 232 base_provider = "NousResearch",
285 233 best_provider = Airforce
286 234 )
@@ -305,12 +253,6 @@ phi_2 = Model(
305 253 best_provider = IterListProvider([Cloudflare, Airforce])
306 254 )
307 255
308 phi_3_medium_4k = Model(
309 name = "phi-3-medium-4k",
310 base_provider = "Microsoft",
311 best_provider = None
312 )
313
314 256 phi_3_5_mini = Model(
315 257 name = "phi-3.5-mini",
316 258 base_provider = "Microsoft",
@@ -322,13 +264,13 @@ phi_3_5_mini = Model(
322 264 gemini_pro = Model(
323 265 name = 'gemini-pro',
324 266 base_provider = 'Google DeepMind',
325 best_provider = IterListProvider([GeminiPro, Blackbox, AIChatFree, FreeGpt, Airforce, Liaobots])
267 best_provider = IterListProvider([GeminiPro, Blackbox, AIChatFree, FreeGpt, Liaobots])
326 268 )
327 269
328 270 gemini_flash = Model(
329 271 name = 'gemini-flash',
330 272 base_provider = 'Google DeepMind',
331 best_provider = IterListProvider([Blackbox, GizAI, Airforce, Liaobots])
273 best_provider = IterListProvider([Blackbox, GizAI, Liaobots])
332 274 )
333 275
334 276 gemini = Model(
@@ -341,13 +283,7 @@ gemini = Model(
341 283 gemma_2b = Model(
342 284 name = 'gemma-2b',
343 285 base_provider = 'Google',
344 best_provider = IterListProvider([ReplicateHome, Airforce])
345 )
346
347 gemma_2b_27b = Model(
348 name = 'gemma-2b-27b',
349 base_provider = 'Google',
350 best_provider = IterListProvider([Airforce])
286 best_provider = IterListProvider([ReplicateHome])
351 287 )
352 288
353 289 gemma_7b = Model(
@@ -356,13 +292,6 @@ gemma_7b = Model(
356 292 best_provider = Cloudflare
357 293 )
358 294
359 # gemma 2
360 gemma_2_9b = Model(
361 name = 'gemma-2-9b',
362 base_provider = 'Google',
363 best_provider = Airforce
364 )
365
366 295
367 296 ### Anthropic ###
368 297 claude_2_1 = Model(
@@ -419,15 +348,6 @@ blackboxai_pro = Model(
419 348 best_provider = Blackbox
420 349 )
421 350
422
423 ### Databricks ###
424 dbrx_instruct = Model(
425 name = 'dbrx-instruct',
426 base_provider = 'Databricks',
427 best_provider = IterListProvider([Airforce])
428 )
429
430
431 351 ### CohereForAI ###
432 352 command_r_plus = Model(
433 353 name = 'command-r-plus',
@@ -466,28 +386,10 @@ qwen_1_5_14b = Model(
466 386 qwen_2_72b = Model(
467 387 name = 'qwen-2-72b',
468 388 base_provider = 'Qwen',
469 best_provider = IterListProvider([DeepInfraChat, HuggingChat, Airforce, HuggingFace])
470 )
471
472 qwen_2_5_7b = Model(
473 name = 'qwen-2-5-7b',
474 base_provider = 'Qwen',
475 best_provider = Airforce
476 )
477
478 qwen_2_5_72b = Model(
479 name = 'qwen-2-5-72b',
480 base_provider = 'Qwen',
481 best_provider = Airforce
389 best_provider = IterListProvider([DeepInfraChat, HuggingChat, HuggingFace])
482 390 )
483 391
484 392 ### Upstage ###
485 solar_10_7b = Model(
486 name = 'solar-10-7b',
487 base_provider = 'Upstage',
488 best_provider = Airforce
489 )
490
491 393 solar_mini = Model(
492 394 name = 'solar-mini',
493 395 base_provider = 'Upstage',
@@ -519,7 +421,7 @@ deepseek_coder = Model(
519 421 wizardlm_2_8x22b = Model(
520 422 name = 'wizardlm-2-8x22b',
521 423 base_provider = 'WizardLM',
522 best_provider = IterListProvider([DeepInfraChat, Airforce])
424 best_provider = IterListProvider([DeepInfraChat])
523 425 )
524 426
525 427 ### Yorickvp ###
@@ -529,44 +431,11 @@ llava_13b = Model(
529 431 best_provider = ReplicateHome
530 432 )
531 433
532
533 ### OpenBMB ###
534 minicpm_llama_3_v2_5 = Model(
535 name = 'minicpm-llama-3-v2.5',
536 base_provider = 'OpenBMB',
537 best_provider = None
538 )
539
540
541 ### Lzlv ###
542 lzlv_70b = Model(
543 name = 'lzlv-70b',
544 base_provider = 'Lzlv',
545 best_provider = None
546 )
547
548
549 434 ### OpenChat ###
550 openchat_3_6_8b = Model(
551 name = 'openchat-3.6-8b',
435 openchat_3_5 = Model(
436 name = 'openchat-3.5',
552 437 base_provider = 'OpenChat',
553 best_provider = None
554 )
555
556
557 ### Phind ###
558 phind_codellama_34b_v2 = Model(
559 name = 'phind-codellama-34b-v2',
560 base_provider = 'Phind',
561 best_provider = None
562 )
563
564
565 ### Cognitive Computations ###
566 dolphin_2_9_1_llama_3_70b = Model(
567 name = 'dolphin-2.9.1-llama-3-70b',
568 base_provider = 'Cognitive Computations',
569 best_provider = None
438 best_provider = Airforce
570 439 )
571 440
572 441
@@ -650,6 +519,13 @@ zephyr_7b = Model(
650 519 best_provider = Airforce
651 520 )
652 521
522 ### Inferless ###
523 neural_7b = Model(
524 name = 'neural-7b',
525 base_provider = 'inferless',
526 best_provider = Airforce
527 )
528
653 529
654 530
655 531 #############
@@ -660,7 +536,7 @@ zephyr_7b = Model(
660 536 sdxl = Model(
661 537 name = 'sdxl',
662 538 base_provider = 'Stability AI',
663 best_provider = IterListProvider([ReplicateHome, Airforce])
539 best_provider = IterListProvider([ReplicateHome])
664 540
665 541 )
666 542
@@ -740,7 +616,7 @@ flux_4o = Model(
740 616 flux_schnell = Model(
741 617 name = 'flux-schnell',
742 618 base_provider = 'Flux AI',
743 best_provider = IterListProvider([ReplicateHome])
619 best_provider = ReplicateHome
744 620
745 621 )
746 622
@@ -786,7 +662,6 @@ class ModelUtils:
786 662
787 663 # llama-2
788 664 'llama-2-7b': llama_2_7b,
789 'llama-2-13b': llama_2_13b,
790 665
791 666 # llama-3
792 667 'llama-3-8b': llama_3_8b,
@@ -799,33 +674,23 @@ class ModelUtils:
799 674
800 675 # llama-3.2
801 676 'llama-3.2-1b': llama_3_2_1b,
802 'llama-3.2-3b': llama_3_2_3b,
803 677 'llama-3.2-11b': llama_3_2_11b,
804 'llama-3.2-90b': llama_3_2_90b,
805
806 # llamaguard
807 'llamaguard-7b': llamaguard_7b,
808 'llamaguard-2-8b': llamaguard_2_8b,
809 'llamaguard-3-8b': llamaguard_3_8b,
810 'llamaguard-3-11b': llamaguard_3_11b,
811
678
812 679
813 680 ### Mistral ###
814 681 'mistral-7b': mistral_7b,
815 682 'mixtral-8x7b': mixtral_8x7b,
816 'mixtral-8x22b': mixtral_8x22b,
817 683 'mistral-nemo': mistral_nemo,
818 684
819 685
820 686 ### NousResearch ###
821 'hermes-2': hermes_2,
687 'hermes-2-pro': hermes_2_pro,
822 688 'hermes-2-dpo': hermes_2_dpo,
823 689 'hermes-3': hermes_3,
824 690
825 691
826 692 ### Microsoft ###
827 693 'phi-2': phi_2,
828 'phi_3_medium-4k': phi_3_medium_4k,
829 694 'phi-3.5-mini': phi_3_5_mini,
830 695
831 696
@@ -837,12 +702,8 @@ class ModelUtils:
837 702
838 703 # gemma
839 704 'gemma-2b': gemma_2b,
840 'gemma-2b-27b': gemma_2b_27b,
841 705 'gemma-7b': gemma_7b,
842 706
843 # gemma-2
844 'gemma-2-9b': gemma_2_9b,
845
846 707
847 708 ### Anthropic ###
848 709 'claude-2.1': claude_2_1,
@@ -868,10 +729,6 @@ class ModelUtils:
868 729 ### CohereForAI ###
869 730 'command-r+': command_r_plus,
870 731
871
872 ### Databricks ###
873 'dbrx-instruct': dbrx_instruct,
874
875 732
876 733 ### GigaChat ###
877 734 'gigachat': gigachat,
@@ -887,14 +744,9 @@ class ModelUtils:
887 744
888 745 # qwen 2
889 746 'qwen-2-72b': qwen_2_72b,
890
891 # qwen 2-5
892 'qwen-2-5-7b': qwen_2_5_7b,
893 'qwen-2-5-72b': qwen_2_5_72b,
894
747
895 748
896 749 ### Upstage ###
897 'solar-10-7b': solar_10_7b,
898 750 'solar-mini': solar_mini,
899 751 'solar-pro': solar_pro,
900 752
@@ -913,27 +765,11 @@ class ModelUtils:
913 765
914 766 ### WizardLM ###
915 767 'wizardlm-2-8x22b': wizardlm_2_8x22b,
916
917
918 ### OpenBMB ###
919 'minicpm-llama-3-v2.5': minicpm_llama_3_v2_5,
920
921
922 ### Lzlv ###
923 'lzlv-70b': lzlv_70b,
924
768
925 769
926 770 ### OpenChat ###
927 'openchat-3.6-8b': openchat_3_6_8b,
928
929
930 ### Phind ###
931 'phind-codellama-34b-v2': phind_codellama_34b_v2,
932
933
934 ### Cognitive Computations ###
935 'dolphin-2.9.1-llama-3-70b': dolphin_2_9_1_llama_3_70b,
936
771 'openchat-3.5': openchat_3_5,
772
937 773
938 774 ### x.ai ###
939 775 'grok-2': grok_2,
@@ -972,6 +808,10 @@ class ModelUtils:
972 808
973 809 ### HuggingFaceH4 ###
974 810 'zephyr-7b': zephyr_7b,
811
812
813 ### Inferless ###
814 'neural-7b': neural_7b,
975 815
976 816
977 817