Update Needed: Judgment model options are undocumented

[KevinNV]

Currently, the list of acceptable models for judgement in README is not specified. For example, the model in the code below has a complex name and the exact models aren't mentioned anywhere.

judgment.async_evaluate(
        scorers=[AnswerRelevancyScorer(threshold=0.5)],
        input=user_input,
        actual_output=content,
        model="meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
    )

Suggested Fixes:
Publicly document available models, or maybe create a helper function that can list all available models.

[linear]

JUD-1402 Update Needed: Judgment model options are undocumented