Skip to main content

[Serverless] How to get your model ID and access token

Written by Promptitude Team

To use the Hugging Face Inference API, you’ll need two key values:

  • Model ID

  • Access token

This guide will help you collect both.

Prerequisites

  • An active Hugging Face account

  • An active Access Token with the correct configuration settings enabled

  • A valid text-generation Model ID that corresponds to the model you wish to use in Promptitude

📌 Remember, Serverless functionality is available with Enterprise plans in Promptitude.

Step-by-Step Guide

1️⃣ Create your Access Token

  1. Log in to https://huggingface.co/

  2. Open your profile dropdown.

  3. Select Access Tokens from the menu:

  4. Click the “Create new token” button:

  5. Select the Fine-grained option and enter a name for the token. In the Inference section, be sure to check the following options to configure the access token properly:

    • Make calls to the serverless Inference API

    • Make calls to Inference Endpoints

  6. Click the Create Token button at the bottom of the page to generate the token.

  7. A popup will appear displaying your newly created token. Copy the token and save it in a secure location, as you’ll need it to add to Promptitude later:

2️⃣ Get your Model Id

Currently, only text-generation models are supported in Promptitude. You can find the available models at the following URL: Models - Hugging FaceModels - Hugging Face

Step-by-Step Guide

  1. From the list, select the text-generation model you'd like to add to Promptitude.

  2. In the model card, locate and copy the Model ID for use in Promptitude.
    ​

3️⃣ Configure your Serverless Inference API connection in Promptitude.io

  1. Go to the Serverless Inference API Hub page and click the New Inference API Provider button:

  2. In the slide-over panel, give a name to your new Inference API provider and click the Save button:

  3. Once the provider is created, you'll be redirected to the provider's models. From here, click Add Endpoint Model:

  4. Configure all the properties you previously obtained in order to add your available model. Make sure that the properties are correct, click Save:

  5. If everything went well, you will see your model in the table:

  6. Now you can use your model in your prompts:

Summary 📌

By following these steps, you will have gathered the following information:

  • Access Token

  • Model ID

After obtaining this information you will be able to configure and use the models you have configured within your Promptitude.io account.

Related Articles
Did this answer your question?