This tutorial will walk you through the steps to use LMStudio to download the Llama model and set up an inference server. Instead of Llama models that is just used as an example, you can download any open source models. LMStudio can be installed on the kiosk computer or a server on the local network where the kiosks are installed.

Step 1: Installing LMStudio

1. Go to the LMStudio website (https://lmstudio.io/) and click on the "Download" button to download the latest version of LMStudio.
2. Follow the installation instructions for your operating system.

Step 2: Launching LMStudio

1. Once LMStudio is installed, launch the application.
2. Log in to your LMStudio account or create a new account if you do not already have one.

Step 3: Downloading the Llama model

1. In the LMStudio main menu, click on the "Models" tab.
2. In the "Available Models" section, find the Llama model and click on the "Download" button.
3. The model will be downloaded and added to your list of available models.

Step 4: Setting up an inference server

1. In the LMStudio main menu, click on the "Servers" tab (double arrows).
2. Click on the "Create Server" button to create a new inference server.
3. Give your server a name and select the Llama model from the "Model" dropdown menu.
4. Choose the hardware resources you want to allocate to your server, including the number of CPU cores and the amount of memory.
5. Click on the "Create" button to create your server.
6. Once your server is created, you can start and stop it by clicking on the "Start" and "Stop" buttons.

That's it! You should now have an inference server running the Llama model and be able to make conversations using the API endpoint that can be used with HelloKiosk (API URL)