LLaMA 3.1 405B Instruct

LLaMA 3.1 405B Instruct

LLaMA v3.1 405B Instruct

by

Meta

Model ID:

Llama-3.1-405b-instruct

Use This Model

Model Overview

FAQs

Related Links

Overview

LLaMA v3.1 405B Instruct is the largest model in the LLaMA 3.1 series, featuring 405 billion parameters. It is designed for high-level reasoning and complex problem-solving, making it a powerful tool for advanced applications in AI research and development.

Specializations

  • Largest LLaMA Model: State-of-the-art performance across various tasks.

  • Instruction-Tuned: Optimized for following instructions and generating text.

Integration Guide (Javascript)

To use this model through Portkey, follow these steps:

1. Install Portkey SDK:

npm install --save portkey-ai

2. Set up client with Portkey:

// Import and initialize Portkey

import Portkey from 'portkey-ai'

const portkey = new Portkey({

  apiKey: "PORTKEY_API_KEY", // Replace with your Portkey API key

  virtualKey: "VIRTUAL_KEY" // Your Fireworks Virtual Key created in Portkey

})

3. Make a request:

// Make a chat completion request

const chatCompletion = await portkey.chat.completions.create({

  messages: [{ role: 'user', content: 'Say this is a test' }],

  model: 'accounts/fireworks/models/llama-v3p1-405b-instruct',

});

console.log(chatCompletion.choices);

Live API Statistics and Performace Metrics

LMSys Arena Elo Score:

1266

Arena Score

LMSys Leaderboard Rank:

7

Arena Rank

Evaluates LLMs through a combination of user feedback and automated scoring systems.

Model Specifications

Release Date:

23/7/2024

Model Variants:

accounts/fireworks/models/llama-v3p1-405b-instruct

Max. Context Tokens:

128K

Max. Output Tokens:

8K

Model Size

405B

Knowledge Cut-Off Date:

December 2023

MMLU:

87.3

%

License:

Open-Source

Technical Report/Model Card:

LMSys Elo Score

1266

Pricing

$/Million Input Tokens

$

3

$/Million Output Tokens

$

3

Live updates via Portkey Pricing API. Coming Soon...

© 2024 Portkey, Inc. All rights reserved