From 466bf7dc9c3ffc0502cf3f63a53655d024cb2a9c Mon Sep 17 00:00:00 2001 From: timothycarambat Date: Wed, 31 Jul 2024 10:58:34 -0700 Subject: [PATCH] Bump Perplexity and Together AI static model list --- server/utils/AiProviders/perplexity/index.js | 2 +- server/utils/AiProviders/perplexity/models.js | 30 ++++++ .../perplexity/scripts/chat_models.txt | 22 +++-- .../AiProviders/perplexity/scripts/parse.mjs | 2 +- server/utils/AiProviders/togetherAi/models.js | 96 ++++++++++++++++--- .../togetherAi/scripts/chat_models.txt | 22 ++++- .../AiProviders/togetherAi/scripts/parse.mjs | 2 +- 7 files changed, 148 insertions(+), 28 deletions(-) diff --git a/server/utils/AiProviders/perplexity/index.js b/server/utils/AiProviders/perplexity/index.js index 43830663..712605f0 100644 --- a/server/utils/AiProviders/perplexity/index.js +++ b/server/utils/AiProviders/perplexity/index.js @@ -21,7 +21,7 @@ class PerplexityLLM { this.model = modelPreference || process.env.PERPLEXITY_MODEL_PREF || - "sonar-small-online"; // Give at least a unique model to the provider as last fallback. + "llama-3-sonar-large-32k-online"; // Give at least a unique model to the provider as last fallback. this.limits = { history: this.promptWindowLimit() * 0.15, system: this.promptWindowLimit() * 0.15, diff --git a/server/utils/AiProviders/perplexity/models.js b/server/utils/AiProviders/perplexity/models.js index 124e3ea1..f20ce70c 100644 --- a/server/utils/AiProviders/perplexity/models.js +++ b/server/utils/AiProviders/perplexity/models.js @@ -19,6 +19,26 @@ const MODELS = { name: "llama-3-sonar-large-32k-chat", maxLength: 32768, }, + "llama-3.1-sonar-small-128k-online": { + id: "llama-3.1-sonar-small-128k-online", + name: "llama-3.1-sonar-small-128k-online", + maxLength: 127072, + }, + "llama-3.1-sonar-small-128k-chat": { + id: "llama-3.1-sonar-small-128k-chat", + name: "llama-3.1-sonar-small-128k-chat", + maxLength: 131072, + }, + "llama-3.1-sonar-large-128k-online": { + id: "llama-3.1-sonar-large-128k-online", + name: "llama-3.1-sonar-large-128k-online", + maxLength: 127072, + }, + "llama-3.1-sonar-large-128k-chat": { + id: "llama-3.1-sonar-large-128k-chat", + name: "llama-3.1-sonar-large-128k-chat", + maxLength: 131072, + }, "llama-3-8b-instruct": { id: "llama-3-8b-instruct", name: "llama-3-8b-instruct", @@ -34,6 +54,16 @@ const MODELS = { name: "mixtral-8x7b-instruct", maxLength: 16384, }, + "llama-3.1-8b-instruct": { + id: "llama-3.1-8b-instruct", + name: "llama-3.1-8b-instruct", + maxLength: 131072, + }, + "llama-3.1-70b-instruct": { + id: "llama-3.1-70b-instruct", + name: "llama-3.1-70b-instruct", + maxLength: 131072, + }, }; module.exports.MODELS = MODELS; diff --git a/server/utils/AiProviders/perplexity/scripts/chat_models.txt b/server/utils/AiProviders/perplexity/scripts/chat_models.txt index 2d2d34f7..8e98f0c2 100644 --- a/server/utils/AiProviders/perplexity/scripts/chat_models.txt +++ b/server/utils/AiProviders/perplexity/scripts/chat_models.txt @@ -1,9 +1,15 @@ -| Model | Parameter Count | Context Length | Model Type | -| :--------------------------------- | :-------------- | :------------- | :-------------- | -| `llama-3-sonar-small-32k-online` | 8B | 28,000 | Chat Completion | -| `llama-3-sonar-small-32k-chat` | 8B | 32,768 | Chat Completion | -| `llama-3-sonar-large-32k-online` | 70B | 28,000 | Chat Completion | -| `llama-3-sonar-large-32k-chat` | 70B | 32,768 | Chat Completion | -| `llama-3-8b-instruct` | 8B | 8,192 | Chat Completion | +| Model | Parameter Count | Context Length | Model Type | +| :---------------------------------- | :-------------- | :------------- | :-------------- | +| `llama-3-sonar-small-32k-online` | 8B | 28,000 | Chat Completion | +| `llama-3-sonar-small-32k-chat` | 8B | 32,768 | Chat Completion | +| `llama-3-sonar-large-32k-online` | 70B | 28,000 | Chat Completion | +| `llama-3-sonar-large-32k-chat` | 70B | 32,768 | Chat Completion | +| `llama-3.1-sonar-small-128k-online` | 8B | 127,072 | Chat Completion | +| `llama-3.1-sonar-small-128k-chat` | 8B | 131,072 | Chat Completion | +| `llama-3.1-sonar-large-128k-online` | 70B | 127,072 | Chat Completion | +| `llama-3.1-sonar-large-128k-chat` | 70B | 131,072 | Chat Completion | +| `llama-3-8b-instruct` | 8B | 8,192 | Chat Completion | | `llama-3-70b-instruct` | 70B | 8,192 | Chat Completion | -| `mixtral-8x7b-instruct` | 8x7B | 16,384 | Chat Completion | \ No newline at end of file +| `mixtral-8x7b-instruct` | 8x7B | 16,384 | Chat Completion | +| `llama-3.1-8b-instruct` | 8B | 131,072 | Chat Completion | +| `llama-3.1-70b-instruct` | 70B | 131,072 | Chat Completion | \ No newline at end of file diff --git a/server/utils/AiProviders/perplexity/scripts/parse.mjs b/server/utils/AiProviders/perplexity/scripts/parse.mjs index 6dec22d9..e4f27276 100644 --- a/server/utils/AiProviders/perplexity/scripts/parse.mjs +++ b/server/utils/AiProviders/perplexity/scripts/parse.mjs @@ -8,7 +8,7 @@ // copy outputs into the export in ../models.js // Update the date below if you run this again because Perplexity added new models. -// Last Collected: Jul 19, 2024 +// Last Collected: Jul 31, 2024 import fs from "fs"; diff --git a/server/utils/AiProviders/togetherAi/models.js b/server/utils/AiProviders/togetherAi/models.js index 79ab93ba..c6b884c4 100644 --- a/server/utils/AiProviders/togetherAi/models.js +++ b/server/utils/AiProviders/togetherAi/models.js @@ -1,16 +1,70 @@ const MODELS = { - "zero-one-ai/Yi-34B-Chat": { - id: "zero-one-ai/Yi-34B-Chat", - organization: "01.AI", - name: "01-ai Yi Chat (34B)", + "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + id: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", + organization: "Meta", + name: "Llama 3.1 8B Instruct Turbo", + maxLength: 128000, + }, + "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + id: "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", + organization: "Meta", + name: "Llama 3.1 70B Instruct Turbo", + maxLength: 128000, + }, + "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { + id: "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", + organization: "Meta", + name: "Llama 3.1 405B Instruct Turbo", maxLength: 4096, }, + "meta-llama/Meta-Llama-3-8B-Instruct-Turbo": { + id: "meta-llama/Meta-Llama-3-8B-Instruct-Turbo", + organization: "Meta", + name: "Llama 3 8B Instruct Turbo", + maxLength: 8192, + }, + "meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + id: "meta-llama/Meta-Llama-3-70B-Instruct-Turbo", + organization: "Meta", + name: "Llama 3 70B Instruct Turbo", + maxLength: 8192, + }, + "meta-llama/Meta-Llama-3-8B-Instruct-Lite": { + id: "meta-llama/Meta-Llama-3-8B-Instruct-Lite", + organization: "Meta", + name: "Llama 3 8B Instruct Lite", + maxLength: 8192, + }, + "meta-llama/Meta-Llama-3-70B-Instruct-Lite": { + id: "meta-llama/Meta-Llama-3-70B-Instruct-Lite", + organization: "Meta", + name: "Llama 3 70B Instruct Lite", + maxLength: 8192, + }, + "google/gemma-2-27b-it": { + id: "google/gemma-2-27b-it", + organization: "Google", + name: "Gemma 2 27B", + maxLength: 8192, + }, + "google/gemma-2-9b-it": { + id: "google/gemma-2-9b-it", + organization: "Google", + name: "Gemma 2 9B", + maxLength: 8192, + }, "allenai/OLMo-7B-Instruct": { id: "allenai/OLMo-7B-Instruct", organization: "Allen AI", name: "OLMo Instruct (7B)", maxLength: 2048, }, + "zero-one-ai/Yi-34B-Chat": { + id: "zero-one-ai/Yi-34B-Chat", + organization: "01.AI", + name: "01-ai Yi Chat (34B)", + maxLength: 4096, + }, "allenai/OLMo-7B-Twin-2T": { id: "allenai/OLMo-7B-Twin-2T", organization: "Allen AI", @@ -135,19 +189,13 @@ const MODELS = { id: "meta-llama/Llama-3-8b-chat-hf", organization: "Meta", name: "LLaMA-3 Chat (8B)", - maxLength: 8000, + maxLength: 8192, }, "meta-llama/Llama-3-70b-chat-hf": { id: "meta-llama/Llama-3-70b-chat-hf", organization: "Meta", name: "LLaMA-3 Chat (70B)", - maxLength: 8000, - }, - "microsoft/WizardLM-2-8x22B": { - id: "microsoft/WizardLM-2-8x22B", - organization: "Microsoft", - name: "WizardLM-2 (8x22B)", - maxLength: 65536, + maxLength: 8192, }, "mistralai/Mistral-7B-Instruct-v0.1": { id: "mistralai/Mistral-7B-Instruct-v0.1", @@ -161,6 +209,12 @@ const MODELS = { name: "Mistral (7B) Instruct v0.2", maxLength: 32768, }, + "mistralai/Mistral-7B-Instruct-v0.3": { + id: "mistralai/Mistral-7B-Instruct-v0.3", + organization: "mistralai", + name: "Mistral (7B) Instruct v0.3", + maxLength: 32768, + }, "mistralai/Mixtral-8x7B-Instruct-v0.1": { id: "mistralai/Mixtral-8x7B-Instruct-v0.1", organization: "mistralai", @@ -269,12 +323,30 @@ const MODELS = { name: "Qwen 1.5 Chat (72B)", maxLength: 32768, }, + "Qwen/Qwen1.5-110B-Chat": { + id: "Qwen/Qwen1.5-110B-Chat", + organization: "Qwen", + name: "Qwen 1.5 Chat (110B)", + maxLength: 32768, + }, + "Qwen/Qwen2-72B-Instruct": { + id: "Qwen/Qwen2-72B-Instruct", + organization: "Qwen", + name: "Qwen 2 Instruct (72B)", + maxLength: 32768, + }, "snorkelai/Snorkel-Mistral-PairRM-DPO": { id: "snorkelai/Snorkel-Mistral-PairRM-DPO", organization: "Snorkel AI", name: "Snorkel Mistral PairRM DPO (7B)", maxLength: 32768, }, + "Snowflake/snowflake-arctic-instruct": { + id: "Snowflake/snowflake-arctic-instruct", + organization: "Snowflake", + name: "Snowflake Arctic Instruct", + maxLength: 4096, + }, "togethercomputer/alpaca-7b": { id: "togethercomputer/alpaca-7b", organization: "Stanford", diff --git a/server/utils/AiProviders/togetherAi/scripts/chat_models.txt b/server/utils/AiProviders/togetherAi/scripts/chat_models.txt index 499d2354..2c69d757 100644 --- a/server/utils/AiProviders/togetherAi/scripts/chat_models.txt +++ b/server/utils/AiProviders/togetherAi/scripts/chat_models.txt @@ -1,7 +1,16 @@ | Organization | Model Name | Model String for API | Context length | -| --- | --- | --- | --- | -| 01.AI | 01-ai Yi Chat (34B) | zero-one-ai/Yi-34B-Chat | 4096 | +|--------------|------------|----------------------|----------------| +| Meta | Llama 3.1 8B Instruct Turbo | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | 128000 | +| Meta | Llama 3.1 70B Instruct Turbo | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 128000 | +| Meta | Llama 3.1 405B Instruct Turbo | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 4096 | +| Meta | Llama 3 8B Instruct Turbo | meta-llama/Meta-Llama-3-8B-Instruct-Turbo | 8192 | +| Meta | Llama 3 70B Instruct Turbo | meta-llama/Meta-Llama-3-70B-Instruct-Turbo | 8192 | +| Meta | Llama 3 8B Instruct Lite | meta-llama/Meta-Llama-3-8B-Instruct-Lite | 8192 | +| Meta | Llama 3 70B Instruct Lite | meta-llama/Meta-Llama-3-70B-Instruct-Lite | 8192 | +| Google | Gemma 2 27B | google/gemma-2-27b-it | 8192 | +| Google | Gemma 2 9B | google/gemma-2-9b-it | 8192 | | Allen AI | OLMo Instruct (7B) | allenai/OLMo-7B-Instruct | 2048 | +| 01.AI | 01-ai Yi Chat (34B) | zero-one-ai/Yi-34B-Chat | 4096 | | Allen AI | OLMo Twin-2T (7B) | allenai/OLMo-7B-Twin-2T | 2048 | | Allen AI | OLMo (7B) | allenai/OLMo-7B | 2048 | | Austism | Chronos Hermes (13B) | Austism/chronos-hermes-13b | 2048 | @@ -22,11 +31,11 @@ | Meta | LLaMA-2 Chat (70B) | meta-llama/Llama-2-70b-chat-hf | 4096 | | Meta | LLaMA-2 Chat (13B) | meta-llama/Llama-2-13b-chat-hf | 4096 | | Meta | LLaMA-2 Chat (7B) | meta-llama/Llama-2-7b-chat-hf | 4096 | -| Meta | LLaMA-3 Chat (8B) | meta-llama/Llama-3-8b-chat-hf | 8000 | -| Meta | LLaMA-3 Chat (70B) | meta-llama/Llama-3-70b-chat-hf | 8000 | -| Microsoft | WizardLM-2 (8x22B) | microsoft/WizardLM-2-8x22B | 65536 | +| Meta | LLaMA-3 Chat (8B) | meta-llama/Llama-3-8b-chat-hf | 8192 | +| Meta | LLaMA-3 Chat (70B) | meta-llama/Llama-3-70b-chat-hf | 8192 | | mistralai | Mistral (7B) Instruct | mistralai/Mistral-7B-Instruct-v0.1 | 8192 | | mistralai | Mistral (7B) Instruct v0.2 | mistralai/Mistral-7B-Instruct-v0.2 | 32768 | +| mistralai | Mistral (7B) Instruct v0.3 | mistralai/Mistral-7B-Instruct-v0.3 | 32768 | | mistralai | Mixtral-8x7B Instruct (46.7B) | mistralai/Mixtral-8x7B-Instruct-v0.1 | 32768 | | mistralai | Mixtral-8x22B Instruct (141B) | mistralai/Mixtral-8x22B-Instruct-v0.1 | 65536 | | NousResearch | Nous Capybara v1.9 (7B) | NousResearch/Nous-Capybara-7B-V1p9 | 8192 | @@ -45,7 +54,10 @@ | Qwen | Qwen 1.5 Chat (14B) | Qwen/Qwen1.5-14B-Chat | 32768 | | Qwen | Qwen 1.5 Chat (32B) | Qwen/Qwen1.5-32B-Chat | 32768 | | Qwen | Qwen 1.5 Chat (72B) | Qwen/Qwen1.5-72B-Chat | 32768 | +| Qwen | Qwen 1.5 Chat (110B) | Qwen/Qwen1.5-110B-Chat | 32768 | +| Qwen | Qwen 2 Instruct (72B) | Qwen/Qwen2-72B-Instruct | 32768 | | Snorkel AI | Snorkel Mistral PairRM DPO (7B) | snorkelai/Snorkel-Mistral-PairRM-DPO | 32768 | +| Snowflake | Snowflake Arctic Instruct | Snowflake/snowflake-arctic-instruct | 4096 | | Stanford | Alpaca (7B) | togethercomputer/alpaca-7b | 2048 | | Teknium | OpenHermes-2-Mistral (7B) | teknium/OpenHermes-2-Mistral-7B | 8192 | | Teknium | OpenHermes-2.5-Mistral (7B) | teknium/OpenHermes-2p5-Mistral-7B | 8192 | diff --git a/server/utils/AiProviders/togetherAi/scripts/parse.mjs b/server/utils/AiProviders/togetherAi/scripts/parse.mjs index 7d5d6277..69f14140 100644 --- a/server/utils/AiProviders/togetherAi/scripts/parse.mjs +++ b/server/utils/AiProviders/togetherAi/scripts/parse.mjs @@ -8,7 +8,7 @@ // copy outputs into the export in ../models.js // Update the date below if you run this again because TogetherAI added new models. -// Last Collected: Apr 18, 2024 +// Last Collected: Jul 31, 2024 // Since last collection Together's docs are broken. I just copied the HTML table // and had claude3 convert to markdown and it works well enough.