mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2025-04-17 18:18:11 +00:00
Dynamic fetching of TogetherAI models (#3017)
* implement dynamic fetching of togetherai models * implement caching for togetherai models * update gitignore for togetherai model caching * Remove models.json from git tracking * Remove .cached_at from git tracking * lint * revert unneeded change --------- Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
This commit is contained in:
Sean Hatfield
GitHub
parent
273d116586
commit
48dcb22b25
8 changed files with 133 additions and 818 deletions
frontend/src/components/LLMSelection/TogetherAiOptions
server
storage/models
utils
AiProviders/togetherAi
helpers
|
|
@ -2,6 +2,9 @@ import System from "@/models/system";
|
|||
import { useState, useEffect } from "react";
|
||||
|
||||
export default function TogetherAiOptions({ settings }) {
|
||||
const [inputValue, setInputValue] = useState(settings?.TogetherAiApiKey);
|
||||
const [apiKey, setApiKey] = useState(settings?.TogetherAiApiKey);
|
||||
|
||||
return (
|
||||
<div className="flex gap-[36px] mt-1.5">
|
||||
<div className="flex flex-col w-60">
|
||||
|
|
@ -17,37 +20,49 @@ export default function TogetherAiOptions({ settings }) {
|
|||
required={true}
|
||||
autoComplete="off"
|
||||
spellCheck={false}
|
||||
onChange={(e) => setInputValue(e.target.value)}
|
||||
onBlur={() => setApiKey(inputValue)}
|
||||
/>
|
||||
</div>
|
||||
{!settings?.credentialsOnly && (
|
||||
<TogetherAiModelSelection settings={settings} />
|
||||
<TogetherAiModelSelection settings={settings} apiKey={apiKey} />
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
function TogetherAiModelSelection({ settings }) {
|
||||
|
||||
function TogetherAiModelSelection({ settings, apiKey }) {
|
||||
const [groupedModels, setGroupedModels] = useState({});
|
||||
const [loading, setLoading] = useState(true);
|
||||
|
||||
useEffect(() => {
|
||||
async function findCustomModels() {
|
||||
setLoading(true);
|
||||
const { models } = await System.customModels("togetherai");
|
||||
|
||||
if (models?.length > 0) {
|
||||
const modelsByOrganization = models.reduce((acc, model) => {
|
||||
acc[model.organization] = acc[model.organization] || [];
|
||||
acc[model.organization].push(model);
|
||||
return acc;
|
||||
}, {});
|
||||
|
||||
setGroupedModels(modelsByOrganization);
|
||||
try {
|
||||
const key = apiKey === "*".repeat(20) ? null : apiKey;
|
||||
const { models } = await System.customModels("togetherai", key);
|
||||
if (models?.length > 0) {
|
||||
const modelsByOrganization = models.reduce((acc, model) => {
|
||||
if (model.type !== "chat") return acc; // Only show chat models in dropdown
|
||||
const org = model.organization || "Unknown";
|
||||
acc[org] = acc[org] || [];
|
||||
acc[org].push({
|
||||
id: model.id,
|
||||
name: model.name || model.id,
|
||||
organization: org,
|
||||
maxLength: model.maxLength,
|
||||
});
|
||||
return acc;
|
||||
}, {});
|
||||
setGroupedModels(modelsByOrganization);
|
||||
}
|
||||
} catch (error) {
|
||||
console.error("Error fetching Together AI models:", error);
|
||||
}
|
||||
|
||||
setLoading(false);
|
||||
}
|
||||
findCustomModels();
|
||||
}, []);
|
||||
}, [apiKey]);
|
||||
|
||||
if (loading || Object.keys(groupedModels).length === 0) {
|
||||
return (
|
||||
|
|
|
|||
3
server/storage/models/.gitignore
vendored
3
server/storage/models/.gitignore
vendored
|
|
@ -5,4 +5,5 @@ openrouter
|
|||
apipie
|
||||
novita
|
||||
mixedbread-ai*
|
||||
gemini
|
||||
gemini
|
||||
togetherAi
|
||||
|
|
@ -5,10 +5,76 @@ const {
|
|||
const {
|
||||
LLMPerformanceMonitor,
|
||||
} = require("../../helpers/chat/LLMPerformanceMonitor");
|
||||
const fs = require("fs");
|
||||
const path = require("path");
|
||||
const { safeJsonParse } = require("../../http");
|
||||
|
||||
function togetherAiModels() {
|
||||
const { MODELS } = require("./models.js");
|
||||
return MODELS || {};
|
||||
const cacheFolder = path.resolve(
|
||||
process.env.STORAGE_DIR
|
||||
? path.resolve(process.env.STORAGE_DIR, "models", "togetherAi")
|
||||
: path.resolve(__dirname, `../../../storage/models/togetherAi`)
|
||||
);
|
||||
|
||||
async function togetherAiModels(apiKey = null) {
|
||||
const cacheModelPath = path.resolve(cacheFolder, "models.json");
|
||||
const cacheAtPath = path.resolve(cacheFolder, ".cached_at");
|
||||
|
||||
// If cache exists and is less than 1 week old, use it
|
||||
if (fs.existsSync(cacheModelPath) && fs.existsSync(cacheAtPath)) {
|
||||
const now = Number(new Date());
|
||||
const timestampMs = Number(fs.readFileSync(cacheAtPath));
|
||||
if (now - timestampMs <= 6.048e8) {
|
||||
// 1 Week in MS
|
||||
return safeJsonParse(
|
||||
fs.readFileSync(cacheModelPath, { encoding: "utf-8" }),
|
||||
[]
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
try {
|
||||
const { OpenAI: OpenAIApi } = require("openai");
|
||||
const openai = new OpenAIApi({
|
||||
baseURL: "https://api.together.xyz/v1",
|
||||
apiKey: apiKey || process.env.TOGETHER_AI_API_KEY || null,
|
||||
});
|
||||
|
||||
const response = await openai.models.list();
|
||||
|
||||
// Filter and transform models into the expected format
|
||||
// Only include chat models
|
||||
const validModels = response.body
|
||||
.filter((model) => ["chat"].includes(model.type))
|
||||
.map((model) => ({
|
||||
id: model.id,
|
||||
name: model.display_name || model.id,
|
||||
organization: model.organization || "Unknown",
|
||||
type: model.type,
|
||||
maxLength: model.context_length || 4096,
|
||||
}));
|
||||
|
||||
// Cache the results
|
||||
if (!fs.existsSync(cacheFolder))
|
||||
fs.mkdirSync(cacheFolder, { recursive: true });
|
||||
fs.writeFileSync(cacheModelPath, JSON.stringify(validModels), {
|
||||
encoding: "utf-8",
|
||||
});
|
||||
fs.writeFileSync(cacheAtPath, String(Number(new Date())), {
|
||||
encoding: "utf-8",
|
||||
});
|
||||
|
||||
return validModels;
|
||||
} catch (error) {
|
||||
console.error("Error fetching Together AI models:", error);
|
||||
// If cache exists but is stale, still use it as fallback
|
||||
if (fs.existsSync(cacheModelPath)) {
|
||||
return safeJsonParse(
|
||||
fs.readFileSync(cacheModelPath, { encoding: "utf-8" }),
|
||||
[]
|
||||
);
|
||||
}
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
class TogetherAiLLM {
|
||||
|
|
@ -60,29 +126,34 @@ class TogetherAiLLM {
|
|||
return content.flat();
|
||||
}
|
||||
|
||||
allModelInformation() {
|
||||
return togetherAiModels();
|
||||
async allModelInformation() {
|
||||
const models = await togetherAiModels();
|
||||
return models.reduce((acc, model) => {
|
||||
acc[model.id] = model;
|
||||
return acc;
|
||||
}, {});
|
||||
}
|
||||
|
||||
streamingEnabled() {
|
||||
return "streamGetChatCompletion" in this;
|
||||
}
|
||||
|
||||
static promptWindowLimit(modelName) {
|
||||
const availableModels = togetherAiModels();
|
||||
return availableModels[modelName]?.maxLength || 4096;
|
||||
static async promptWindowLimit(modelName) {
|
||||
const models = await togetherAiModels();
|
||||
const model = models.find((m) => m.id === modelName);
|
||||
return model?.maxLength || 4096;
|
||||
}
|
||||
|
||||
// Ensure the user set a value for the token limit
|
||||
// and if undefined - assume 4096 window.
|
||||
promptWindowLimit() {
|
||||
const availableModels = this.allModelInformation();
|
||||
return availableModels[this.model]?.maxLength || 4096;
|
||||
async promptWindowLimit() {
|
||||
const models = await togetherAiModels();
|
||||
const model = models.find((m) => m.id === this.model);
|
||||
return model?.maxLength || 4096;
|
||||
}
|
||||
|
||||
async isValidChatCompletionModel(model = "") {
|
||||
const availableModels = this.allModelInformation();
|
||||
return availableModels.hasOwnProperty(model);
|
||||
const models = await togetherAiModels();
|
||||
const foundModel = models.find((m) => m.id === model);
|
||||
return foundModel && foundModel.type === "chat";
|
||||
}
|
||||
|
||||
constructPrompt({
|
||||
|
|
|
|||
|
|
@ -1,622 +0,0 @@
|
|||
const MODELS = {
|
||||
"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-Instruct": {
|
||||
id: "allenai/OLMo-7B-Instruct",
|
||||
organization: "AllenAI",
|
||||
name: "OLMo Instruct (7B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"Austism/chronos-hermes-13b": {
|
||||
id: "Austism/chronos-hermes-13b",
|
||||
organization: "Austism",
|
||||
name: "Chronos Hermes (13B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"carson/ml318br": {
|
||||
id: "carson/ml318br",
|
||||
organization: "carson",
|
||||
name: "carson ml318br",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"cognitivecomputations/dolphin-2.5-mixtral-8x7b": {
|
||||
id: "cognitivecomputations/dolphin-2.5-mixtral-8x7b",
|
||||
organization: "cognitivecomputations",
|
||||
name: "Dolphin 2.5 Mixtral 8x7b",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"databricks/dbrx-instruct": {
|
||||
id: "databricks/dbrx-instruct",
|
||||
organization: "Databricks",
|
||||
name: "DBRX Instruct",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"deepseek-ai/deepseek-llm-67b-chat": {
|
||||
id: "deepseek-ai/deepseek-llm-67b-chat",
|
||||
organization: "DeepSeek",
|
||||
name: "DeepSeek LLM Chat (67B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"deepseek-ai/deepseek-coder-33b-instruct": {
|
||||
id: "deepseek-ai/deepseek-coder-33b-instruct",
|
||||
organization: "DeepSeek",
|
||||
name: "Deepseek Coder Instruct (33B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"garage-bAInd/Platypus2-70B-instruct": {
|
||||
id: "garage-bAInd/Platypus2-70B-instruct",
|
||||
organization: "garage-bAInd",
|
||||
name: "Platypus2 Instruct (70B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"google/gemma-2-9b-it": {
|
||||
id: "google/gemma-2-9b-it",
|
||||
organization: "google",
|
||||
name: "Gemma-2 Instruct (9B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"google/gemma-2b-it": {
|
||||
id: "google/gemma-2b-it",
|
||||
organization: "Google",
|
||||
name: "Gemma Instruct (2B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"google/gemma-2-27b-it": {
|
||||
id: "google/gemma-2-27b-it",
|
||||
organization: "Google",
|
||||
name: "Gemma-2 Instruct (27B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"google/gemma-7b-it": {
|
||||
id: "google/gemma-7b-it",
|
||||
organization: "Google",
|
||||
name: "Gemma Instruct (7B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"gradientai/Llama-3-70B-Instruct-Gradient-1048k": {
|
||||
id: "gradientai/Llama-3-70B-Instruct-Gradient-1048k",
|
||||
organization: "gradientai",
|
||||
name: "Llama-3 70B Instruct Gradient 1048K",
|
||||
maxLength: 1048576,
|
||||
},
|
||||
"Gryphe/MythoMax-L2-13b": {
|
||||
id: "Gryphe/MythoMax-L2-13b",
|
||||
organization: "Gryphe",
|
||||
name: "MythoMax-L2 (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"Gryphe/MythoMax-L2-13b-Lite": {
|
||||
id: "Gryphe/MythoMax-L2-13b-Lite",
|
||||
organization: "Gryphe",
|
||||
name: "Gryphe MythoMax L2 Lite (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"llava-hf/llava-v1.6-mistral-7b-hf": {
|
||||
id: "llava-hf/llava-v1.6-mistral-7b-hf",
|
||||
organization: "Haotian Liu",
|
||||
name: "LLaVa-Next (Mistral-7B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"HuggingFaceH4/zephyr-7b-beta": {
|
||||
id: "HuggingFaceH4/zephyr-7b-beta",
|
||||
organization: "HuggingFace",
|
||||
name: "Zephyr-7B-ß",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"togethercomputer/Koala-7B": {
|
||||
id: "togethercomputer/Koala-7B",
|
||||
organization: "LM Sys",
|
||||
name: "Koala (7B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"lmsys/vicuna-7b-v1.3": {
|
||||
id: "lmsys/vicuna-7b-v1.3",
|
||||
organization: "LM Sys",
|
||||
name: "Vicuna v1.3 (7B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"lmsys/vicuna-13b-v1.5-16k": {
|
||||
id: "lmsys/vicuna-13b-v1.5-16k",
|
||||
organization: "LM Sys",
|
||||
name: "Vicuna v1.5 16K (13B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"lmsys/vicuna-13b-v1.5": {
|
||||
id: "lmsys/vicuna-13b-v1.5",
|
||||
organization: "LM Sys",
|
||||
name: "Vicuna v1.5 (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"lmsys/vicuna-13b-v1.3": {
|
||||
id: "lmsys/vicuna-13b-v1.3",
|
||||
organization: "LM Sys",
|
||||
name: "Vicuna v1.3 (13B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"togethercomputer/Koala-13B": {
|
||||
id: "togethercomputer/Koala-13B",
|
||||
organization: "LM Sys",
|
||||
name: "Koala (13B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"lmsys/vicuna-7b-v1.5": {
|
||||
id: "lmsys/vicuna-7b-v1.5",
|
||||
organization: "LM Sys",
|
||||
name: "Vicuna v1.5 (7B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"codellama/CodeLlama-34b-Instruct-hf": {
|
||||
id: "codellama/CodeLlama-34b-Instruct-hf",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (34B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"togethercomputer/Llama-3-8b-chat-hf-int4": {
|
||||
id: "togethercomputer/Llama-3-8b-chat-hf-int4",
|
||||
organization: "Meta",
|
||||
name: "Llama3 8B Chat HF INT4",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
|
||||
id: "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Llama 3.2 90B Vision Instruct Turbo",
|
||||
maxLength: 131072,
|
||||
},
|
||||
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
|
||||
id: "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Llama 3.2 11B Vision Instruct Turbo",
|
||||
maxLength: 131072,
|
||||
},
|
||||
"meta-llama/Llama-3.2-3B-Instruct-Turbo": {
|
||||
id: "meta-llama/Llama-3.2-3B-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.2 3B Instruct Turbo",
|
||||
maxLength: 131072,
|
||||
},
|
||||
"togethercomputer/Llama-3-8b-chat-hf-int8": {
|
||||
id: "togethercomputer/Llama-3-8b-chat-hf-int8",
|
||||
organization: "Meta",
|
||||
name: "Togethercomputer Llama3 8B Instruct Int8",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
|
||||
id: "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 70B Instruct Turbo",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"meta-llama/Llama-2-13b-chat-hf": {
|
||||
id: "meta-llama/Llama-2-13b-chat-hf",
|
||||
organization: "Meta",
|
||||
name: "LLaMA-2 Chat (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
|
||||
id: "meta-llama/Meta-Llama-3-70B-Instruct-Lite",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 70B Instruct Lite",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Llama-3-8b-chat-hf": {
|
||||
id: "meta-llama/Llama-3-8b-chat-hf",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 8B Instruct Reference",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Llama-3-70b-chat-hf": {
|
||||
id: "meta-llama/Llama-3-70b-chat-hf",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 70B Instruct Reference",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo": {
|
||||
id: "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 8B Instruct Turbo",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3-8B-Instruct-Lite": {
|
||||
id: "meta-llama/Meta-Llama-3-8B-Instruct-Lite",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 8B Instruct Lite",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro": {
|
||||
id: "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 405B Instruct Turbo",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"meta-llama/Llama-2-7b-chat-hf": {
|
||||
id: "meta-llama/Llama-2-7b-chat-hf",
|
||||
organization: "Meta",
|
||||
name: "LLaMA-2 Chat (7B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
|
||||
id: "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 405B Instruct Turbo",
|
||||
maxLength: 130815,
|
||||
},
|
||||
"meta-llama/Llama-Vision-Free": {
|
||||
id: "meta-llama/Llama-Vision-Free",
|
||||
organization: "Meta",
|
||||
name: "(Free) Llama 3.2 11B Vision Instruct Turbo",
|
||||
maxLength: 131072,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
|
||||
id: "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 70B Instruct Turbo",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
|
||||
id: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 8B Instruct Turbo",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"togethercomputer/CodeLlama-7b-Instruct": {
|
||||
id: "togethercomputer/CodeLlama-7b-Instruct",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (7B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"togethercomputer/CodeLlama-34b-Instruct": {
|
||||
id: "togethercomputer/CodeLlama-34b-Instruct",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (34B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"codellama/CodeLlama-13b-Instruct-hf": {
|
||||
id: "codellama/CodeLlama-13b-Instruct-hf",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (13B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"togethercomputer/CodeLlama-13b-Instruct": {
|
||||
id: "togethercomputer/CodeLlama-13b-Instruct",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (13B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"togethercomputer/llama-2-13b-chat": {
|
||||
id: "togethercomputer/llama-2-13b-chat",
|
||||
organization: "Meta",
|
||||
name: "LLaMA-2 Chat (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"togethercomputer/llama-2-7b-chat": {
|
||||
id: "togethercomputer/llama-2-7b-chat",
|
||||
organization: "Meta",
|
||||
name: "LLaMA-2 Chat (7B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3-8B-Instruct": {
|
||||
id: "meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 8B Instruct",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3-70B-Instruct": {
|
||||
id: "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3 70B Instruct",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"codellama/CodeLlama-70b-Instruct-hf": {
|
||||
id: "codellama/CodeLlama-70b-Instruct-hf",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (70B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"togethercomputer/llama-2-70b-chat": {
|
||||
id: "togethercomputer/llama-2-70b-chat",
|
||||
organization: "Meta",
|
||||
name: "LLaMA-2 Chat (70B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"codellama/CodeLlama-7b-Instruct-hf": {
|
||||
id: "codellama/CodeLlama-7b-Instruct-hf",
|
||||
organization: "Meta",
|
||||
name: "Code Llama Instruct (7B)",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"meta-llama/Llama-2-70b-chat-hf": {
|
||||
id: "meta-llama/Llama-2-70b-chat-hf",
|
||||
organization: "Meta",
|
||||
name: "LLaMA-2 Chat (70B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3.1-8B-Instruct-Reference": {
|
||||
id: "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 8B Instruct",
|
||||
maxLength: 16384,
|
||||
},
|
||||
"albert/meta-llama-3-1-70b-instruct-turbo": {
|
||||
id: "albert/meta-llama-3-1-70b-instruct-turbo",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 70B Instruct Turbo",
|
||||
maxLength: 131072,
|
||||
},
|
||||
"meta-llama/Meta-Llama-3.1-70B-Instruct-Reference": {
|
||||
id: "meta-llama/Meta-Llama-3.1-70B-Instruct-Reference",
|
||||
organization: "Meta",
|
||||
name: "Meta Llama 3.1 70B Instruct",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"microsoft/WizardLM-2-8x22B": {
|
||||
id: "microsoft/WizardLM-2-8x22B",
|
||||
organization: "microsoft",
|
||||
name: "WizardLM-2 (8x22B)",
|
||||
maxLength: 65536,
|
||||
},
|
||||
"mistralai/Mistral-7B-Instruct-v0.1": {
|
||||
id: "mistralai/Mistral-7B-Instruct-v0.1",
|
||||
organization: "mistralai",
|
||||
name: "Mistral (7B) Instruct",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"mistralai/Mistral-7B-Instruct-v0.2": {
|
||||
id: "mistralai/Mistral-7B-Instruct-v0.2",
|
||||
organization: "mistralai",
|
||||
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",
|
||||
name: "Mixtral-8x7B Instruct v0.1",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
|
||||
id: "mistralai/Mixtral-8x22B-Instruct-v0.1",
|
||||
organization: "mistralai",
|
||||
name: "Mixtral-8x22B Instruct v0.1",
|
||||
maxLength: 65536,
|
||||
},
|
||||
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
|
||||
id: "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Hermes 2 - Mixtral 8x7B-DPO",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"NousResearch/Nous-Hermes-Llama2-70b": {
|
||||
id: "NousResearch/Nous-Hermes-Llama2-70b",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Hermes LLaMA-2 (70B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT": {
|
||||
id: "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Hermes 2 - Mixtral 8x7B-SFT",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"NousResearch/Nous-Hermes-Llama2-13b": {
|
||||
id: "NousResearch/Nous-Hermes-Llama2-13b",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Hermes Llama-2 (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"NousResearch/Nous-Hermes-2-Mistral-7B-DPO": {
|
||||
id: "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Hermes 2 - Mistral DPO (7B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"NousResearch/Nous-Hermes-llama-2-7b": {
|
||||
id: "NousResearch/Nous-Hermes-llama-2-7b",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Hermes LLaMA-2 (7B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"NousResearch/Nous-Capybara-7B-V1p9": {
|
||||
id: "NousResearch/Nous-Capybara-7B-V1p9",
|
||||
organization: "NousResearch",
|
||||
name: "Nous Capybara v1.9 (7B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"NousResearch/Hermes-2-Theta-Llama-3-70B": {
|
||||
id: "NousResearch/Hermes-2-Theta-Llama-3-70B",
|
||||
organization: "NousResearch",
|
||||
name: "Hermes 2 Theta Llama-3 70B",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"openchat/openchat-3.5-1210": {
|
||||
id: "openchat/openchat-3.5-1210",
|
||||
organization: "OpenChat",
|
||||
name: "OpenChat 3.5",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"Open-Orca/Mistral-7B-OpenOrca": {
|
||||
id: "Open-Orca/Mistral-7B-OpenOrca",
|
||||
organization: "OpenOrca",
|
||||
name: "OpenOrca Mistral (7B) 8K",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"Qwen/Qwen2-72B-Instruct": {
|
||||
id: "Qwen/Qwen2-72B-Instruct",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 2 Instruct (72B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen2.5-72B-Instruct-Turbo": {
|
||||
id: "Qwen/Qwen2.5-72B-Instruct-Turbo",
|
||||
organization: "Qwen",
|
||||
name: "Qwen2.5 72B Instruct Turbo",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
|
||||
id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
|
||||
organization: "Qwen",
|
||||
name: "Qwen2.5 7B Instruct Turbo",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-110B-Chat": {
|
||||
id: "Qwen/Qwen1.5-110B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (110B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-72B-Chat": {
|
||||
id: "Qwen/Qwen1.5-72B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (72B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen2-1.5B-Instruct": {
|
||||
id: "Qwen/Qwen2-1.5B-Instruct",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 2 Instruct (1.5B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen2-7B-Instruct": {
|
||||
id: "Qwen/Qwen2-7B-Instruct",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 2 Instruct (7B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-14B-Chat": {
|
||||
id: "Qwen/Qwen1.5-14B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (14B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-1.8B-Chat": {
|
||||
id: "Qwen/Qwen1.5-1.8B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (1.8B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-32B-Chat": {
|
||||
id: "Qwen/Qwen1.5-32B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (32B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-7B-Chat": {
|
||||
id: "Qwen/Qwen1.5-7B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (7B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-0.5B-Chat": {
|
||||
id: "Qwen/Qwen1.5-0.5B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (0.5B)",
|
||||
maxLength: 32768,
|
||||
},
|
||||
"Qwen/Qwen1.5-4B-Chat": {
|
||||
id: "Qwen/Qwen1.5-4B-Chat",
|
||||
organization: "Qwen",
|
||||
name: "Qwen 1.5 Chat (4B)",
|
||||
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",
|
||||
name: "Alpaca (7B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"teknium/OpenHermes-2-Mistral-7B": {
|
||||
id: "teknium/OpenHermes-2-Mistral-7B",
|
||||
organization: "teknium",
|
||||
name: "OpenHermes-2-Mistral (7B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"teknium/OpenHermes-2p5-Mistral-7B": {
|
||||
id: "teknium/OpenHermes-2p5-Mistral-7B",
|
||||
organization: "teknium",
|
||||
name: "OpenHermes-2.5-Mistral (7B)",
|
||||
maxLength: 8192,
|
||||
},
|
||||
"test/test11": {
|
||||
id: "test/test11",
|
||||
organization: "test",
|
||||
name: "Test 11",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"togethercomputer/guanaco-65b": {
|
||||
id: "togethercomputer/guanaco-65b",
|
||||
organization: "Tim Dettmers",
|
||||
name: "Guanaco (65B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"togethercomputer/guanaco-13b": {
|
||||
id: "togethercomputer/guanaco-13b",
|
||||
organization: "Tim Dettmers",
|
||||
name: "Guanaco (13B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"togethercomputer/guanaco-33b": {
|
||||
id: "togethercomputer/guanaco-33b",
|
||||
organization: "Tim Dettmers",
|
||||
name: "Guanaco (33B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"togethercomputer/guanaco-7b": {
|
||||
id: "togethercomputer/guanaco-7b",
|
||||
organization: "Tim Dettmers",
|
||||
name: "Guanaco (7B)",
|
||||
maxLength: 2048,
|
||||
},
|
||||
"Undi95/ReMM-SLERP-L2-13B": {
|
||||
id: "Undi95/ReMM-SLERP-L2-13B",
|
||||
organization: "Undi95",
|
||||
name: "ReMM SLERP L2 (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"Undi95/Toppy-M-7B": {
|
||||
id: "Undi95/Toppy-M-7B",
|
||||
organization: "Undi95",
|
||||
name: "Toppy M (7B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"upstage/SOLAR-10.7B-Instruct-v1.0": {
|
||||
id: "upstage/SOLAR-10.7B-Instruct-v1.0",
|
||||
organization: "upstage",
|
||||
name: "Upstage SOLAR Instruct v1 (11B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"togethercomputer/SOLAR-10.7B-Instruct-v1.0-int4": {
|
||||
id: "togethercomputer/SOLAR-10.7B-Instruct-v1.0-int4",
|
||||
organization: "upstage",
|
||||
name: "Upstage SOLAR Instruct v1 (11B)-Int4",
|
||||
maxLength: 4096,
|
||||
},
|
||||
"WizardLM/WizardLM-13B-V1.2": {
|
||||
id: "WizardLM/WizardLM-13B-V1.2",
|
||||
organization: "WizardLM",
|
||||
name: "WizardLM v1.2 (13B)",
|
||||
maxLength: 4096,
|
||||
},
|
||||
};
|
||||
|
||||
module.exports.MODELS = MODELS;
|
||||
|
|
@ -1 +0,0 @@
|
|||
*.json
|
||||
|
|
@ -1,108 +0,0 @@
|
|||
| Organization | Model Name | API Model String | Context length | Quantization |
|
||||
| :-------------------- | :--------------------------------------- | :----------------------------------------------- | :------------- | :----------- |
|
||||
| 01.AI | 01-ai Yi Chat (34B) | zero-one-ai/Yi-34B-Chat | 4096 | FP16 |
|
||||
| AllenAI | OLMo Instruct (7B) | allenai/OLMo-7B-Instruct | 2048 | FP16 |
|
||||
| Austism | Chronos Hermes (13B) | Austism/chronos-hermes-13b | 2048 | FP16 |
|
||||
| carson | carson ml318br | carson/ml318br | 8192 | FP16 |
|
||||
| cognitivecomputations | Dolphin 2.5 Mixtral 8x7b | cognitivecomputations/dolphin-2.5-mixtral-8x7b | 32768 | FP16 |
|
||||
| Databricks | DBRX Instruct | databricks/dbrx-instruct | 32768 | FP16 |
|
||||
| DeepSeek | DeepSeek LLM Chat (67B) | deepseek-ai/deepseek-llm-67b-chat | 4096 | FP16 |
|
||||
| DeepSeek | Deepseek Coder Instruct (33B) | deepseek-ai/deepseek-coder-33b-instruct | 16384 | FP16 |
|
||||
| garage-bAInd | Platypus2 Instruct (70B) | garage-bAInd/Platypus2-70B-instruct | 4096 | FP16 |
|
||||
| google | Gemma-2 Instruct (9B) | google/gemma-2-9b-it | 8192 | FP16 |
|
||||
| Google | Gemma Instruct (2B) | google/gemma-2b-it | 8192 | FP16 |
|
||||
| Google | Gemma-2 Instruct (27B) | google/gemma-2-27b-it | 8192 | FP16 |
|
||||
| Google | Gemma Instruct (7B) | google/gemma-7b-it | 8192 | FP16 |
|
||||
| gradientai | Llama-3 70B Instruct Gradient 1048K | gradientai/Llama-3-70B-Instruct-Gradient-1048k | 1048576 | FP16 |
|
||||
| Gryphe | MythoMax-L2 (13B) | Gryphe/MythoMax-L2-13b | 4096 | FP16 |
|
||||
| Gryphe | Gryphe MythoMax L2 Lite (13B) | Gryphe/MythoMax-L2-13b-Lite | 4096 | FP16 |
|
||||
| Haotian Liu | LLaVa-Next (Mistral-7B) | llava-hf/llava-v1.6-mistral-7b-hf | 4096 | FP16 |
|
||||
| HuggingFace | Zephyr-7B-ß | HuggingFaceH4/zephyr-7b-beta | 32768 | FP16 |
|
||||
| LM Sys | Koala (7B) | togethercomputer/Koala-7B | 2048 | FP16 |
|
||||
| LM Sys | Vicuna v1.3 (7B) | lmsys/vicuna-7b-v1.3 | 2048 | FP16 |
|
||||
| LM Sys | Vicuna v1.5 16K (13B) | lmsys/vicuna-13b-v1.5-16k | 16384 | FP16 |
|
||||
| LM Sys | Vicuna v1.5 (13B) | lmsys/vicuna-13b-v1.5 | 4096 | FP16 |
|
||||
| LM Sys | Vicuna v1.3 (13B) | lmsys/vicuna-13b-v1.3 | 2048 | FP16 |
|
||||
| LM Sys | Koala (13B) | togethercomputer/Koala-13B | 2048 | FP16 |
|
||||
| LM Sys | Vicuna v1.5 (7B) | lmsys/vicuna-7b-v1.5 | 4096 | FP16 |
|
||||
| Meta | Code Llama Instruct (34B) | codellama/CodeLlama-34b-Instruct-hf | 16384 | FP16 |
|
||||
| Meta | Llama3 8B Chat HF INT4 | togethercomputer/Llama-3-8b-chat-hf-int4 | 8192 | FP16 |
|
||||
| Meta | Meta Llama 3.2 90B Vision Instruct Turbo | meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo | 131072 | FP16 |
|
||||
| Meta | Meta Llama 3.2 11B Vision Instruct Turbo | meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo | 131072 | FP16 |
|
||||
| Meta | Meta Llama 3.2 3B Instruct Turbo | meta-llama/Llama-3.2-3B-Instruct-Turbo | 131072 | FP16 |
|
||||
| Meta | Togethercomputer Llama3 8B Instruct Int8 | togethercomputer/Llama-3-8b-chat-hf-int8 | 8192 | FP16 |
|
||||
| Meta | Meta Llama 3.1 70B Instruct Turbo | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 32768 | FP8 |
|
||||
| Meta | LLaMA-2 Chat (13B) | meta-llama/Llama-2-13b-chat-hf | 4096 | FP16 |
|
||||
| Meta | Meta Llama 3 70B Instruct Lite | meta-llama/Meta-Llama-3-70B-Instruct-Lite | 8192 | INT4 |
|
||||
| Meta | Meta Llama 3 8B Instruct Reference | meta-llama/Llama-3-8b-chat-hf | 8192 | FP16 |
|
||||
| Meta | Meta Llama 3 70B Instruct Reference | meta-llama/Llama-3-70b-chat-hf | 8192 | FP16 |
|
||||
| Meta | Meta Llama 3 8B Instruct Turbo | meta-llama/Meta-Llama-3-8B-Instruct-Turbo | 8192 | FP8 |
|
||||
| Meta | Meta Llama 3 8B Instruct Lite | meta-llama/Meta-Llama-3-8B-Instruct-Lite | 8192 | INT4 |
|
||||
| Meta | Meta Llama 3.1 405B Instruct Turbo | meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro | 4096 | FP16 |
|
||||
| Meta | LLaMA-2 Chat (7B) | meta-llama/Llama-2-7b-chat-hf | 4096 | FP16 |
|
||||
| Meta | Meta Llama 3.1 405B Instruct Turbo | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 130815 | FP8 |
|
||||
| Meta | Meta Llama Vision Free | meta-llama/Llama-Vision-Free | 131072 | FP16 |
|
||||
| Meta | Meta Llama 3 70B Instruct Turbo | meta-llama/Meta-Llama-3-70B-Instruct-Turbo | 8192 | FP8 |
|
||||
| Meta | Meta Llama 3.1 8B Instruct Turbo | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | 32768 | FP8 |
|
||||
| Meta | Code Llama Instruct (7B) | togethercomputer/CodeLlama-7b-Instruct | 16384 | FP16 |
|
||||
| Meta | Code Llama Instruct (34B) | togethercomputer/CodeLlama-34b-Instruct | 16384 | FP16 |
|
||||
| Meta | Code Llama Instruct (13B) | codellama/CodeLlama-13b-Instruct-hf | 16384 | FP16 |
|
||||
| Meta | Code Llama Instruct (13B) | togethercomputer/CodeLlama-13b-Instruct | 16384 | FP16 |
|
||||
| Meta | LLaMA-2 Chat (13B) | togethercomputer/llama-2-13b-chat | 4096 | FP16 |
|
||||
| Meta | LLaMA-2 Chat (7B) | togethercomputer/llama-2-7b-chat | 4096 | FP16 |
|
||||
| Meta | Meta Llama 3 8B Instruct | meta-llama/Meta-Llama-3-8B-Instruct | 8192 | FP16 |
|
||||
| Meta | Meta Llama 3 70B Instruct | meta-llama/Meta-Llama-3-70B-Instruct | 8192 | FP16 |
|
||||
| Meta | Code Llama Instruct (70B) | codellama/CodeLlama-70b-Instruct-hf | 4096 | FP16 |
|
||||
| Meta | LLaMA-2 Chat (70B) | togethercomputer/llama-2-70b-chat | 4096 | FP16 |
|
||||
| Meta | Code Llama Instruct (7B) | codellama/CodeLlama-7b-Instruct-hf | 16384 | FP16 |
|
||||
| Meta | LLaMA-2 Chat (70B) | meta-llama/Llama-2-70b-chat-hf | 4096 | FP16 |
|
||||
| Meta | Meta Llama 3.1 8B Instruct | meta-llama/Meta-Llama-3.1-8B-Instruct-Reference | 16384 | FP16 |
|
||||
| Meta | Meta Llama 3.1 70B Instruct Turbo | albert/meta-llama-3-1-70b-instruct-turbo | 131072 | FP16 |
|
||||
| Meta | Meta Llama 3.1 70B Instruct | meta-llama/Meta-Llama-3.1-70B-Instruct-Reference | 8192 | FP16 |
|
||||
| Meta | (Free) Llama 3.2 11B Vision Instruct Turbo | meta-llama/Llama-Vision-Free | 131072 | FP16 |
|
||||
| Meta | Llama 3.2 11B Vision Instruct Turbo | meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo | 131072 | FP16 |
|
||||
| Meta | Llama 3.2 90B Vision Instruct Turbo | meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo | 131072 | FP16 |
|
||||
| microsoft | WizardLM-2 (8x22B) | microsoft/WizardLM-2-8x22B | 65536 | FP16 |
|
||||
| mistralai | Mistral (7B) Instruct | mistralai/Mistral-7B-Instruct-v0.1 | 4096 | FP16 |
|
||||
| mistralai | Mistral (7B) Instruct v0.2 | mistralai/Mistral-7B-Instruct-v0.2 | 32768 | FP16 |
|
||||
| mistralai | Mistral (7B) Instruct v0.3 | mistralai/Mistral-7B-Instruct-v0.3 | 32768 | FP16 |
|
||||
| mistralai | Mixtral-8x7B Instruct v0.1 | mistralai/Mixtral-8x7B-Instruct-v0.1 | 32768 | FP16 |
|
||||
| mistralai | Mixtral-8x22B Instruct v0.1 | mistralai/Mixtral-8x22B-Instruct-v0.1 | 65536 | FP16 |
|
||||
| NousResearch | Nous Hermes 2 - Mixtral 8x7B-DPO | NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | 32768 | FP16 |
|
||||
| NousResearch | Nous Hermes LLaMA-2 (70B) | NousResearch/Nous-Hermes-Llama2-70b | 4096 | FP16 |
|
||||
| NousResearch | Nous Hermes 2 - Mixtral 8x7B-SFT | NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT | 32768 | FP16 |
|
||||
| NousResearch | Nous Hermes Llama-2 (13B) | NousResearch/Nous-Hermes-Llama2-13b | 4096 | FP16 |
|
||||
| NousResearch | Nous Hermes 2 - Mistral DPO (7B) | NousResearch/Nous-Hermes-2-Mistral-7B-DPO | 32768 | FP16 |
|
||||
| NousResearch | Nous Hermes LLaMA-2 (7B) | NousResearch/Nous-Hermes-llama-2-7b | 4096 | FP16 |
|
||||
| NousResearch | Nous Capybara v1.9 (7B) | NousResearch/Nous-Capybara-7B-V1p9 | 8192 | FP16 |
|
||||
| NousResearch | Hermes 2 Theta Llama-3 70B | NousResearch/Hermes-2-Theta-Llama-3-70B | 8192 | FP16 |
|
||||
| OpenChat | OpenChat 3.5 | openchat/openchat-3.5-1210 | 8192 | FP16 |
|
||||
| OpenOrca | OpenOrca Mistral (7B) 8K | Open-Orca/Mistral-7B-OpenOrca | 8192 | FP16 |
|
||||
| Qwen | Qwen 2 Instruct (72B) | Qwen/Qwen2-72B-Instruct | 32768 | FP16 |
|
||||
| Qwen | Qwen2.5 72B Instruct Turbo | Qwen/Qwen2.5-72B-Instruct-Turbo | 32768 | FP8 |
|
||||
| Qwen | Qwen2.5 7B Instruct Turbo | Qwen/Qwen2.5-7B-Instruct-Turbo | 32768 | FP8 |
|
||||
| Qwen | Qwen 1.5 Chat (110B) | Qwen/Qwen1.5-110B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (72B) | Qwen/Qwen1.5-72B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 2 Instruct (1.5B) | Qwen/Qwen2-1.5B-Instruct | 32768 | FP16 |
|
||||
| Qwen | Qwen 2 Instruct (7B) | Qwen/Qwen2-7B-Instruct | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (14B) | Qwen/Qwen1.5-14B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (1.8B) | Qwen/Qwen1.5-1.8B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (32B) | Qwen/Qwen1.5-32B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (7B) | Qwen/Qwen1.5-7B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (0.5B) | Qwen/Qwen1.5-0.5B-Chat | 32768 | FP16 |
|
||||
| Qwen | Qwen 1.5 Chat (4B) | Qwen/Qwen1.5-4B-Chat | 32768 | FP16 |
|
||||
| Snorkel AI | Snorkel Mistral PairRM DPO (7B) | snorkelai/Snorkel-Mistral-PairRM-DPO | 32768 | FP16 |
|
||||
| Snowflake | Snowflake Arctic Instruct | Snowflake/snowflake-arctic-instruct | 4096 | FP16 |
|
||||
| Stanford | Alpaca (7B) | togethercomputer/alpaca-7b | 2048 | FP16 |
|
||||
| teknium | OpenHermes-2-Mistral (7B) | teknium/OpenHermes-2-Mistral-7B | 8192 | FP16 |
|
||||
| teknium | OpenHermes-2.5-Mistral (7B) | teknium/OpenHermes-2p5-Mistral-7B | 8192 | FP16 |
|
||||
| test | Test 11 | test/test11 | 4096 | FP16 |
|
||||
| Tim Dettmers | Guanaco (65B) | togethercomputer/guanaco-65b | 2048 | FP16 |
|
||||
| Tim Dettmers | Guanaco (13B) | togethercomputer/guanaco-13b | 2048 | FP16 |
|
||||
| Tim Dettmers | Guanaco (33B) | togethercomputer/guanaco-33b | 2048 | FP16 |
|
||||
| Tim Dettmers | Guanaco (7B) | togethercomputer/guanaco-7b | 2048 | FP16 |
|
||||
| Undi95 | ReMM SLERP L2 (13B) | Undi95/ReMM-SLERP-L2-13B | 4096 | FP16 |
|
||||
| Undi95 | Toppy M (7B) | Undi95/Toppy-M-7B | 4096 | FP16 |
|
||||
| upstage | Upstage SOLAR Instruct v1 (11B) | upstage/SOLAR-10.7B-Instruct-v1.0 | 4096 | FP16 |
|
||||
| upstage | Upstage SOLAR Instruct v1 (11B)-Int4 | togethercomputer/SOLAR-10.7B-Instruct-v1.0-int4 | 4096 | FP16 |
|
||||
| WizardLM | WizardLM v1.2 (13B) | WizardLM/WizardLM-13B-V1.2 | 4096 | FP16 |
|
||||
|
|
@ -1,43 +0,0 @@
|
|||
// Together AI does not provide a simple REST API to get models,
|
||||
// so we have a table which we copy from their documentation
|
||||
// https://docs.together.ai/edit/inference-models that we can
|
||||
// then parse and get all models from in a format that makes sense
|
||||
// Why this does not exist is so bizarre, but whatever.
|
||||
|
||||
// To run, cd into this directory and run `node parse.mjs`
|
||||
// copy outputs into the export in ../models.js
|
||||
|
||||
// Update the date below if you run this again because TogetherAI added new models.
|
||||
// Last Collected: Nov 20, 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.
|
||||
|
||||
import fs from "fs";
|
||||
|
||||
function parseChatModels() {
|
||||
const fixed = {};
|
||||
const tableString = fs.readFileSync("chat_models.txt", { encoding: "utf-8" });
|
||||
const rows = tableString.split("\n").slice(2);
|
||||
|
||||
rows.forEach((row) => {
|
||||
const [provider, name, id, maxLength] = row.split("|").slice(1, -1);
|
||||
const data = {
|
||||
provider: provider.trim(),
|
||||
name: name.trim(),
|
||||
id: id.trim(),
|
||||
maxLength: Number(maxLength.trim()),
|
||||
};
|
||||
|
||||
fixed[data.id] = {
|
||||
id: data.id,
|
||||
organization: data.provider,
|
||||
name: data.name,
|
||||
maxLength: data.maxLength,
|
||||
};
|
||||
});
|
||||
|
||||
fs.writeFileSync("chat_models.json", JSON.stringify(fixed, null, 2), "utf-8");
|
||||
return fixed;
|
||||
}
|
||||
|
||||
parseChatModels();
|
||||
|
|
@ -44,7 +44,7 @@ async function getCustomModels(provider = "", apiKey = null, basePath = null) {
|
|||
case "ollama":
|
||||
return await ollamaAIModels(basePath);
|
||||
case "togetherai":
|
||||
return await getTogetherAiModels();
|
||||
return await getTogetherAiModels(apiKey);
|
||||
case "fireworksai":
|
||||
return await getFireworksAiModels(apiKey);
|
||||
case "mistral":
|
||||
|
|
@ -327,19 +327,21 @@ async function ollamaAIModels(basePath = null) {
|
|||
return { models, error: null };
|
||||
}
|
||||
|
||||
async function getTogetherAiModels() {
|
||||
const knownModels = togetherAiModels();
|
||||
if (!Object.keys(knownModels).length === 0)
|
||||
return { models: [], error: null };
|
||||
|
||||
const models = Object.values(knownModels).map((model) => {
|
||||
return {
|
||||
id: model.id,
|
||||
organization: model.organization,
|
||||
name: model.name,
|
||||
};
|
||||
});
|
||||
return { models, error: null };
|
||||
async function getTogetherAiModels(apiKey = null) {
|
||||
const _apiKey =
|
||||
apiKey === true
|
||||
? process.env.TOGETHER_AI_API_KEY
|
||||
: apiKey || process.env.TOGETHER_AI_API_KEY || null;
|
||||
try {
|
||||
const { togetherAiModels } = require("../AiProviders/togetherAi");
|
||||
const models = await togetherAiModels(_apiKey);
|
||||
if (models.length > 0 && !!_apiKey)
|
||||
process.env.TOGETHER_AI_API_KEY = _apiKey;
|
||||
return { models, error: null };
|
||||
} catch (error) {
|
||||
console.error("Error in getTogetherAiModels:", error);
|
||||
return { models: [], error: "Failed to fetch Together AI models" };
|
||||
}
|
||||
}
|
||||
|
||||
async function getFireworksAiModels() {
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue