Added llm-judge support for GPT-4o

[danielwetzel]

trafficstars

Why are these changes needed?

The simple changes add GPT-4o support to the llm-judge. As GPT-4o is much faster & much cheaper compared to GPT-4 (+ also better in terms of quality), this poses to be a useful addition. The default judge of GPT-4 is not touched yet, but with the arg "--judge-model gpt-4o" the new GPT model can be used for the gen_judgment.py function.

Related issue number (if applicable)

I couldn't find an issue related to the addition. But since this is such a small addition, I don't think an issue is required.

Checks

• [ ✅ ] I've run format.sh to lint the changes in this PR. ("Your code has been rated at 9.03/10")
• [ ✅ ] I've included any doc changes needed.
• [ not applicable ] I've made sure the relevant tests are passing (if applicable). ( I have looked through all the tests, but none of those seem applicable for the changes I added )