Official

meta / llama-2-70b-chat

A 70 billion parameter language model from Meta, fine tuned for chat completions

  • Public
  • 9.3M runs
  • Priced per token
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README

Run replicate-internal/llama-2-70b-chat-int8-4xa100-80gb-triton with an API

Use one of our client libraries to get started quickly.

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Learn more about authentication

Install Replicate’s Node.js client library

npm install replicate
Learn more about setup

Run meta/llama-2-70b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

import Replicate from "replicate";
const replicate = new Replicate();

const input = {
    top_p: 1,
    prompt: "Can you write a poem about open source machine learning? Let's make it in the style of E. E. Cummings.",
    temperature: 0.5,
    max_new_tokens: 500,
    min_new_tokens: -1
};

for await (const event of replicate.stream("meta/llama-2-70b-chat", { input })) {
  process.stdout.write(`${event}`)
};

//=> "Sure, here's a poem about open source machine learning i...
Learn more