Generate a model's insights with a large language model (LLM)
You can generate a model's insights with a large language model (LLM). After defining an LLM source, you can generate insights for a model.
By default, H2O Model Validatio utilizes the h2oGPT LLM source to generate insights about a model. To define your own LLM to generate model insights, see Define a large language model (LLM) source.
To generate a model's insights, consider the following instructions:
- In the H2O Model Validation navigation menu, click Models.
- In the Models table, click the name of the model you want to generate its insights.
- Click Insights. note
Right after clicking the Insights button, H2O Model Validation generates and displays the insights of the model.