Merge remote-tracking branch 'upstream/main'

bentwnghk · Sep 1, 2024 · e45fab3 · e45fab3
2 parents 32bb5d9 + f9c043c
commit e45fab3
Show file tree

Hide file tree

Showing 7 changed files with 180 additions and 77 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -127,7 +127,7 @@ ENV \
     # Moonshot
     MOONSHOT_API_KEY="" MOONSHOT_PROXY_URL="" \
     # Novita
-    NOVITA_API_KEY="" \
+    NOVITA_API_KEY="" NOVITA_MODEL_LIST="" \
     # Ollama
     OLLAMA_MODEL_LIST="" OLLAMA_PROXY_URL="" \
     # OpenAI

diff --git a/Dockerfile.database b/Dockerfile.database
@@ -168,7 +168,7 @@ ENV \
     # Moonshot
     MOONSHOT_API_KEY="" MOONSHOT_PROXY_URL="" \
     # Novita
-    NOVITA_API_KEY="" \
+    NOVITA_API_KEY="" NOVITA_MODEL_LIST="" \
     # Ollama
     OLLAMA_MODEL_LIST="" OLLAMA_PROXY_URL="" \
     # OpenAI

diff --git a/src/config/llm.ts b/src/config/llm.ts
@@ -81,6 +81,7 @@ export const getLLMConfig = () => {
 
       ENABLED_NOVITA: z.boolean(),
       NOVITA_API_KEY: z.string().optional(),
+      NOVITA_MODEL_LIST: z.string().optional(),
 
       ENABLED_BAICHUAN: z.boolean(),
       BAICHUAN_API_KEY: z.string().optional(),
@@ -176,6 +177,7 @@ export const getLLMConfig = () => {
 
       ENABLED_NOVITA: !!process.env.NOVITA_API_KEY,
       NOVITA_API_KEY: process.env.NOVITA_API_KEY,
+      NOVITA_MODEL_LIST: process.env.NOVITA_MODEL_LIST,
 
       ENABLED_BAICHUAN: !!process.env.BAICHUAN_API_KEY,
       BAICHUAN_API_KEY: process.env.BAICHUAN_API_KEY,

diff --git a/src/config/modelProviders/novita.ts b/src/config/modelProviders/novita.ts
@@ -1,30 +1,47 @@
 import { ModelProviderCard } from '@/types/llm';
 
+// ref: https://novita.ai/model-api/product/llm-api
 const Novita: ModelProviderCard = {
   chatModels: [
     {
-      displayName: 'Llama3 8B Instruct',
+      displayName: 'Llama3.1 8B Instruct',
+      enabled: true,
+      id: 'meta-llama/llama-3.1-8b-instruct',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama3.1 70B Instruct',
       enabled: true,
+      id: 'meta-llama/llama-3.1-70b-instruct',
+      tokens: 131_072,
+    },
+    {
+      displayName: 'Llama3.1 405B Instruct',
+      enabled: true,
+      id: 'meta-llama/llama-3.1-405b-instruct',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Llama3 8B Instruct',
       id: 'meta-llama/llama-3-8b-instruct',
       tokens: 8192,
     },
     {
       displayName: 'Llama3 70B Instruct',
-      enabled: true,
       id: 'meta-llama/llama-3-70b-instruct',
       tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes 2 Pro - Llama3 8B',
+      displayName: 'Gemma 2 9B',
       enabled: true,
-      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      id: 'google/gemma-2-9b-it',
       tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes - Llama2 8B',
+      displayName: 'Mistral Nemo',
       enabled: true,
-      id: 'nousresearch/nous-hermes-llama2-13b',
-      tokens: 4096,
+      id: 'mistralai/mistral-nemo',
+      tokens: 32_768,
     },
     {
       displayName: 'Mistral 7B Instruct',
@@ -33,55 +50,44 @@ const Novita: ModelProviderCard = {
       tokens: 32_768,
     },
     {
-      displayName: 'Dolphin Mixtral 8x22B',
+      displayName: 'WizardLM 2 7B',
       enabled: true,
-      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
-      tokens: 16_000,
+      id: 'microsoft/wizardlm 2-7b',
+      tokens: 32_768,
     },
     {
-      displayName: 'L3-70b-Euryale-v2.1',
+      displayName: 'WizardLM-2 8x22B',
       enabled: true,
-      id: 'sao10k/l3-70b-euryale-v2.1',
-      tokens: 16_000,
+      id: 'microsoft/wizardlm-2-8x22b',
+      tokens: 65_535,
     },
     {
-      displayName: 'Midnight Rose 70B',
-      enabled: true,
-      id: 'sophosympatheia/midnight-rose-70b',
-      tokens: 4096,
+      displayName: 'Dolphin Mixtral 8x22B',
+      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
+      tokens: 16_000,
     },
     {
-      displayName: 'Mythomax L2 13b',
-      enabled: true,
-      id: 'gryphe/mythomax-l2-13b',
-      tokens: 4096,
+      displayName: 'Hermes 2 Pro Llama 3 8B',
+      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes 2 - Mixtral 8x7B-DPO',
-      enabled: true,
+      displayName: 'Hermes 2 Mixtral 8x7B DPO',
       id: 'Nous-Hermes-2-Mixtral-8x7B-DPO',
       tokens: 32_768,
     },
     {
-      displayName: 'Lzlv 70b',
-      enabled: true,
-      id: 'lzlv_70b',
+      displayName: 'MythoMax l2 13B',
+      id: 'gryphe/mythomax-l2-13b',
       tokens: 4096,
     },
     {
-      displayName: 'Open Hermes 2.5 Mistral 7B',
-      enabled: true,
-      id: 'teknium/openhermes-2.5-mistral-7b',
+      displayName: 'OpenChat 7B',
+      id: 'openchat/openchat-7b',
       tokens: 4096,
     },
-    {
-      displayName: 'Wizardlm2 8x22B',
-      enabled: true,
-      id: 'microsoft/wizardlm-2-8x22b',
-      tokens: 65_535,
-    },
   ],
-  checkModel: 'meta-llama/llama-3-70b-instruct',
+  checkModel: 'meta-llama/llama-3.1-8b-instruct',
   disableBrowserRequest: true,
   id: 'novita',
   modelList: { showModelFetcher: true },

diff --git a/src/config/modelProviders/togetherai.ts b/src/config/modelProviders/togetherai.ts
@@ -1,76 +1,161 @@
 import { ModelProviderCard } from '@/types/llm';
 
-// ref https://docs.together.ai/docs/inference-models
+// ref https://docs.together.ai/docs/chat-models
+// ref https://www.together.ai/pricing
 const TogetherAI: ModelProviderCard = {
   chatModels: [
     {
-      displayName: 'Deepseek Coder Instruct (33B)',
+      displayName: 'Llama 3.1 8B Instruct Turbo',
       enabled: true,
-      id: 'deepseek-ai/deepseek-coder-33b-instruct',
-      tokens: 16_384,
+      id: 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo',
+      tokens: 131_072,
     },
     {
-      displayName: 'Phind Code LLaMA v2 (34B)',
+      displayName: 'Llama 3.1 70B Instruct Turbo',
       enabled: true,
-      id: 'Phind/Phind-CodeLlama-34B-v2',
-      tokens: 16_384,
+      id: 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo',
+      tokens: 131_072,
     },
     {
-      displayName: 'Gemma Instruct (2B)',
+      displayName: 'Llama 3.1 405B Instruct Turbo',
       enabled: true,
-      id: 'google/gemma-2b-it',
+      id: 'meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama 3 8B Instruct Turbo',
+      id: 'meta-llama/Meta-Llama-3-8B-Instruct-Turbo',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama 3 70B Instruct Turbo',
+      id: 'meta-llama/Meta-Llama-3-70B-Instruct-Turbo',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama 3 8B Instruct Lite',
+      id: 'meta-llama/Meta-Llama-3-8B-Instruct-Lite',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama 3 70B Instruct Lite',
+      id: 'meta-llama/Meta-Llama-3-70B-Instruct-Lite',
+      tokens: 8192,
+    },
+    {
+      displayName: 'LLaMA-3 Chat (8B)',
+      id: 'meta-llama/Llama-3-8b-chat-hf',
+      tokens: 8192,
+    },
+    {
+      displayName: 'LLaMA-3 Chat (70B)',
+      id: 'meta-llama/Llama-3-70b-chat-hf',
       tokens: 8192,
     },
     {
       displayName: 'LLaMA-2 Chat (13B)',
-      enabled: true,
       id: 'meta-llama/Llama-2-13b-chat-hf',
       tokens: 4096,
     },
     {
-      displayName: '01-ai Yi Chat (34B)',
+      displayName: 'Gemma 2 9B',
       enabled: true,
-      id: 'zero-one-ai/Yi-34B-Chat',
-      tokens: 4096,
+      id: 'google/gemma-2-9b-it',
+      tokens: 8192,
     },
     {
-      displayName: 'Mixtral-8x7B Instruct (46.7B)',
+      displayName: 'Gemma 2 27B',
       enabled: true,
-      id: 'mistralai/Mixtral-8x7B-Instruct-v0.1',
+      id: 'google/gemma-2-27b-it',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Gemma Instruct (2B)',
+      id: 'google/gemma-2b-it',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Mistral (7B) Instruct v0.3',
+      enabled: true,
+      id: 'mistralai/Mistral-7B-Instruct-v0.3',
       tokens: 32_768,
     },
     {
-      displayName: 'Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B)',
+      displayName: 'Mistral (7B) Instruct v0.2',
+      id: 'mistralai/Mistral-7B-Instruct-v0.2',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Mistral (7B) Instruct',
+      id: 'mistralai/Mistral-7B-Instruct-v0.1',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Mixtral-8x7B Instruct (46.7B)',
       enabled: true,
-      id: 'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO',
+      id: 'mistralai/Mixtral-8x7B-Instruct-v0.1',
       tokens: 32_768,
     },
     {
-      displayName: 'Nous Hermes-2 Yi (34B)',
+      displayName: 'Mixtral-8x22B Instruct (141B)',
       enabled: true,
-      id: 'NousResearch/Nous-Hermes-2-Yi-34B',
-      tokens: 4096,
+      id: 'mistralai/Mixtral-8x22B-Instruct-v0.1',
+      tokens: 65_536,
     },
     {
-      displayName: 'Qwen 1.5 Chat (7B)',
+      displayName: 'DeepSeek LLM Chat (67B)',
       enabled: true,
-      id: 'Qwen/Qwen1.5-7B-Chat',
-      tokens: 32_768,
+      id: 'deepseek-ai/deepseek-llm-67b-chat',
+      tokens: 4096,
     },
     {
-      displayName: 'Qwen 1.5 Chat (32B)',
+      displayName: 'Qwen 2 Instruct (72B)',
       enabled: true,
-      id: 'Qwen/Qwen1.5-32B-Chat',
+      id: 'Qwen/Qwen2-72B-Instruct',
       tokens: 32_768,
     },
     {
       displayName: 'Qwen 1.5 Chat (72B)',
-      enabled: true,
       id: 'Qwen/Qwen1.5-72B-Chat',
       tokens: 32_768,
     },
+    {
+      displayName: 'Qwen 1.5 Chat (110B)',
+      id: 'Qwen/Qwen1.5-110B-Chat',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'DBRX Instruct',
+      id: 'databricks/dbrx-instruct',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Upstage SOLAR Instruct v1 (11B)',
+      id: 'upstage/SOLAR-10.7B-Instruct-v1.0',
+      tokens: 4096,
+    },
+    {
+      displayName: 'Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B)',
+      id: 'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Nous Hermes-2 Yi (34B)',
+      id: 'NousResearch/Nous-Hermes-2-Yi-34B',
+      tokens: 4096,
+    },
+    {
+      displayName: 'MythoMax-L2 (13B)',
+      id: 'Gryphe/MythoMax-L2-13b',
+      tokens: 4096,
+    },
+    {
+      displayName: 'StripedHyena Nous (7B)',
+      id: 'togethercomputer/StripedHyena-Nous-7B',
+      tokens: 32_768,
+    },
   ],
-  checkModel: 'togethercomputer/alpaca-7b',
+  checkModel: 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo',
   id: 'togetherai',
   modelList: { showModelFetcher: true },
   name: 'Together AI',