Skip to content

Playground

Overview

The Playground is an interactive environment that allows you to experiment with pre-trained models provided by Highrise Cloud. It's a sandbox for testing models with your own data without the need for coding.

Using the Playground

Step 1: Access the Playground

Log in to the Highrise Cloud platform and navigate to the Playground section.

Step 2: Select a Model

Choose a model from the list of available models. You can filter models by type or use the search bar to find a specific model.

Step 3: Configure Model Parameters

Before deploying the model, you can adjust the following parameters:

Parameter Description
Temperature Controls the randomness of the model's output.
Max Tokens Sets the maximum number of tokens the model can generate.
Top P Controls the diversity of the generated output.

Parameter Adjustments

Modify these parameters to fine-tune the model's output according to your needs.

Step 4: Enter Your Prompt

In the input field at the bottom of the screen, type your prompt or question that you want the model to respond to.

Step 5: Deploy the Model

Click the "Go to deploy" button to initiate the model's processing of your input. This will deploy the model and display the results.

Step 6: Review the Response

Once the model has processed your input, the response will be displayed in the output area. Review the response to evaluate the model's performance.

Evaluating Performance

Analyze the model's response to ensure it meets your expectations.

Tips for Using the Playground

  • Experiment with Different Prompts: Try various prompts to see how the model responds to different types of inputs.
  • Adjust Parameters for Different Results: Modify the temperature, max tokens, and top P values to fine-tune the model's output.
  • Use the Search Function: If you're looking for a specific model, use the search bar to quickly find it.

Next Steps

After you've experimented with the models in the Playground, you can proceed to the Model Market to explore a wide range of pre-trained models for various applications.

For further details on how to deploy models for production use or further development, refer to the related sections or visit our support page to get started with the platform today.