---
license: apache-2.0
model-index:
- name: metadata-test
  results:
  # AI2 Reasoning Challenge (25-Shot)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
       - type: acc_norm
         name: normalized accuracy
         value: 0.6203071672354948
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/datasets/open-llm-leaderboard/details_
      
  # HellaSwag (10-shot)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
       - type: acc_norm
         name: normalized accuracy
         value: 0.8435570603465445
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/datasets/open-llm-leaderboard/details_

  # TruthfulQA (0-shot)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
       - type: mc2
         value: 0.5744916942762855
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/datasets/open-llm-leaderboard/details_

  # GSM8k (5-shot)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
       - type: acc
         name: accuracy
         value: 0.12736921910538287
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/datasets/open-llm-leaderboard/details_

  # MMLU (5-Shot)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
       - type: acc
         name: accuracy
         value: 0.6107
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/datasets/open-llm-leaderboard/details_

  # Winogrande (5-shot)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
       - type: acc
         name: accuracy
         value: 0.7774269928966061
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/datasets/open-llm-leaderboard/details_


---