minor

    tensor_parallel_size: 2

    gpu_memory_utilization: 0.9

  VLM-R1-MATH:

    provider: vllm

    model_name: omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

    max_tokens: 150

    temperature: 0.7

  # VLM-R1-MATH:

  #   provider: vllm

  #   model_name: omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

  #   max_tokens: 150

  #   temperature: 0.7

  gpt4o:

    provider: openai

    model_name: gpt-4o

    max_tokens: 150

    temperature: 0.7

    presence_penalty: 0.0

    frequency_penalty: 0.0

    max_retries: 3

    timeout: 60

  claude_3_sonnet:

    provider: claude

    model_name: claude-3-7-sonnet-20250219

    max_tokens: 150

    temperature: 0.7

  # gpt4o:

  #   provider: openai

  #   model_name: gpt-4o

  #   max_tokens: 150

  #   temperature: 0.7

  #   presence_penalty: 0.0

  #   frequency_penalty: 0.0

  #   max_retries: 3

  #   timeout: 60

  # claude_3_sonnet:

  #   provider: claude

  #   model_name: claude-3-7-sonnet-20250219

  #   max_tokens: 150

  #   temperature: 0.7

  # Gemini_2.5_flask:

  #     provider: gemini