camenduru/mixtral-8x22b-v0.1-4bit | Run with an API on Replicate

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=camenduru/mixtral-8x22b-v0.1-4bit

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run camenduru/mixtral-8x22b-v0.1-4bit using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "camenduru/mixtral-8x22b-v0.1-4bit:19311ec9d4227938bef381d55edd656d321c0926bd01e52461d77003478695ce",
  {
    input: {
      top_k: 0,
      top_p: 0.8,
      prompt: "Tell me a story about the Cheesecake Kingdom.",
      do_sample: true,
      num_beams: 1,
      temperature: 0.2,
      length_penalty: 1,
      max_new_tokens: 128,
      repetition_penalty: 2
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Import the client:

import replicate

Run camenduru/mixtral-8x22b-v0.1-4bit using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "camenduru/mixtral-8x22b-v0.1-4bit:19311ec9d4227938bef381d55edd656d321c0926bd01e52461d77003478695ce",
    input={
        "top_k": 0,
        "top_p": 0.8,
        "prompt": "Tell me a story about the Cheesecake Kingdom.",
        "do_sample": True,
        "num_beams": 1,
        "temperature": 0.2,
        "length_penalty": 1,
        "max_new_tokens": 128,
        "repetition_penalty": 2
    }
)

print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Run camenduru/mixtral-8x22b-v0.1-4bit using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "camenduru/mixtral-8x22b-v0.1-4bit:19311ec9d4227938bef381d55edd656d321c0926bd01e52461d77003478695ce",
    "input": {
      "top_k": 0,
      "top_p": 0.8,
      "prompt": "Tell me a story about the Cheesecake Kingdom.",
      "do_sample": true,
      "num_beams": 1,
      "temperature": 0.2,
      "length_penalty": 1,
      "max_new_tokens": 128,
      "repetition_penalty": 2
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Tell me a story about the Cheesecake Kingdom. The kingdom was founded by King Arthur, who loved cheescakes more than anything else in this world and wanted to share his love with everyone around him so he created an entire country dedicated just for them! He also made sure that there would always be enough supply of these delicious desserts because if not then people might get angry at each other over something as silly like food (which happens sometimes). So now we have our very own little slice heaven right here on earth 🙂

Generated in

18.8 seconds

Tweak it Iterate in playground Share Report View full prediction

This output was created using a different version of the model, camenduru/mixtral-8x22b-v0.1-4bit:fbde2129.

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru

Input

Output

Run time and cost

Readme

🕸 Replicate

🧬 Code

🌐 Page

🏢 Sponsor