[WIP] eval CLI

[yanxi0830]

run.yaml

version: '2'
built_at: '2024-11-11T21:59:52.074753'
image_name: fireworks
docker_image: null
conda_env: fireworks
apis:
- inference
- telemetry
- datasetio
- eval
- scoring
providers:
  scoring:
  - provider_id: basic-0
    provider_type: inline::basic
    config: {}
  - provider_id: llm-as-judge-0
    provider_type: inline::llm-as-judge
    config: {}
  - provider_id: braintrust-0
    provider_type: inline::braintrust
    config: {}
  datasetio:
  - provider_id: huggingface-0
    provider_type: remote::huggingface
    config: {}
  - provider_id: localfs-0
    provider_type: inline::localfs
    config: {}
  eval:
  - provider_id: meta-reference-0
    provider_type: inline::meta-reference
    config: {}
  inference:
  - provider_id: fireworks-0
    provider_type: remote::fireworks
    config:
      url: https://api.fireworks.ai/inference
      api_key: null
  telemetry:
  - provider_id: meta-reference-0
    provider_type: inline::meta-reference
    config: {}
metadata_store: null
models: 
  - model_id: Llama3.2-3B-Instruct
    provider_id: fireworks-0
  - model_id: Llama3.1-8B-Instruct
    provider_id: fireworks-0
  - model_id: Llama3.1-405B-Instruct
    provider_id: fireworks-0
datasets:
  - dataset_id: mmlu
    provider_id: huggingface-0
    url:
      uri: https://huggingface.co/datasets/llamastack/evals
    metadata:
      path: llama-stack/evals
      name: evals__mmlu__details
      split: train
    dataset_schema:
      input_query:
        type: string
      expected_answer:
        type: string
eval_tasks:
  - eval_task_id: meta-reference-mmlu
    provider_id: meta-reference-0
    dataset_id: mmlu
    scoring_functions:
      - basic::regex_parser_multiple_choice_answer

[yanxi0830]

moved to #30