-
Book Overview & Buying
-
Table Of Contents
Supercharged Coding with GenAI
By :
Now that we have fine-tuned our custom model, we can evaluate how its outputs compare to those of the base model. To do this, navigate to the OpenAI Playground, https://platform.openai.com/playground/chat, select gpt-4o-mini-2024-07-18 as the base model, and click on Compare, as shown in Figure 11.12:

Figure 11.12: Playground comparison selecting the base model to compare
Next, add the fine-tuned model, as shown in Figure 11.13:

Figure 11.13: Adding a model for comparison
We will use the same system message from earlier in the chapter that will be applied to both models:
You will be provided with a Python function signature enclosed with {{{ FUNCTION }}}. Your task is to implement it.
Next, we will enter the same user message as earlier in the chapter:
FUNCTION: {{{def get_quadratic_roots_only_if_real(a:int, b:int, c:int) -> Tuple[float, float] }}}
CODE:
Our comparison can be run by clicking Run, generating responses...