README.md

metadata

license: apache-2.0
model-index:
  - name: MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
    results:
      - 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
            value: 62.8
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
          name: Open LLM Leaderboard
      - 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
            value: 84.21
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
          name: Open LLM Leaderboard
      - 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
            value: 63.43
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
          name: Open LLM Leaderboard
      - 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: 48.57
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
          name: Open LLM Leaderboard
      - 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
            value: 76.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
          name: Open LLM Leaderboard
      - 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
            value: 69.83
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear
          name: Open LLM Leaderboard

models:

• model: meta-math/MetaMath-Mistral-7B parameters: weight: 0.5
• model: mlabonne/NeuralHermes-2.5-Mistral-7B parameters: weight: 0.3 merge_method: linear dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.60
AI2 Reasoning Challenge (25-Shot)	62.80
HellaSwag (10-Shot)	84.21
MMLU (5-Shot)	63.43
TruthfulQA (0-shot)	48.57
Winogrande (5-shot)	76.80
GSM8k (5-shot)	69.83