evalplus.yaml

evalplus:
  resources_servers:
    evalplus:
      entrypoint: app.py
      domain: coding
      verified: false
      description: Function-completion code judged by EvalPlus base + plus tests (HumanEval+, MBPP+)
      value: Improve Python function-completion capabilities
      dataset: humaneval
      num_processes: 8
      min_time_limit: 1.0
      gt_time_limit_factor: 4.0
      evalplus_version: default

evalplus_simple_agent:
  responses_api_agents:
    simple_agent:
      entrypoint: app.py
      resources_server:
        type: resources_servers
        name: evalplus
      model_server:
        type: responses_api_models
        name: policy_model
      datasets:
      - name: example
        type: example
        jsonl_fpath: resources_servers/evalplus/data/example.jsonl
        license: MIT