[FT] Open ai endpoint

[Pommel4711]

Evaluation Short Description

I am attempting to evaluate a model similar to ChatGPT using the OpenAI interface. Is there any way to accomplish this?

Why is this evaluation interesting?

This evaluation is interesting because it would allow for the assessment of models like ChatGPT or custom models using the OpenAI interface.

How used is it in the community?

I believe many people will find this useful, as it can facilitate the evaluation of various models within the OpenAI ecosystem.

Evaluation Metadata

Provide all available resources:

• OpenAI Python