Playground

The Playground is your go-to space for testing trained models directly within the UBIAI platform. It allows you to evaluate how well your model performs by providing instant analysis of your input text. With the Playground, there's no need for external tools: everything happens seamlessly within UBIAI.

How to Use the Playground

1

Navigate to the Playground

• On the left sidebar, click on Playground to access the testing interface.

• The playground can also be accessed from the model dashboard by clicking on the Playground tab

2

Select Your Model

• Choose the trained model you want to test from the dropdown menu.

3

Input Your Text

• Copy and paste your test text into the Input Text field.

4

Run The Model

• UBIAI processes the input text using the selected model and provides immediate results.

5

Review the Output

• View the results in the Output section where UbiAI will output results based on the task and model you are using.

Benefits of the Playground

• Test your model’s performance on-the-spot without needing to deploy or integrate it elsewhere.

• Identify incorrect or missing outputs to refine your training dataset or tweak model parameters.

• The intuitive layout ensures even beginners can test and interpret model results effortlessly.

Model Inference API

After training your model, you can run predictions using our API instead of using it in our playground:

• Go to the model details menu and select the API code button next to the token on the top left.

• Copy/paste the generated code in your application and launch the script (make sure to input your texts in the "inputs" list)