Update judge command to support custom judge models

[devin-ai-integration]

Update Judge Command to Support Custom Judge Models

This PR updates the judge command to support using any model provider for judgment instead of just OpenAI. The following changes were made:

1. Added new parameters to replace --openai-api-key:

   • --judge-model-name
   • --judge-model-url
   • --judge-model-api-key

2. Updated the following files:

   • bin/api/run_docker_eval.sh
   • bin/api/run_openai_judge.sh
   • bin/api/entrypoint.sh
   • llm_judge/gen_judgment.py
   • llm_judge/common.py
   • .github/workflows/run-eval.yaml

3. Maintained backward compatibility with existing --openai-api-key parameter.

4. Updated GitHub workflow to use the new parameters.

Resolve https://linear.app/liquid-ai/issue/GEN-370/update-mt-bench-judge-script-to-use-any-llm-provider
Link to Devin run: https://app.devin.ai/sessions/c81627749854419ead0b59881ff887b0
Requested by: liren@liquid.ai

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add "(aside)" to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring