README.md

metadata

license: llama3
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - mlabonne/NeuralDaredevil-8B-abliterated
  - nbeerbower/llama-3-spicy-abliterated-stella-8B
  - flammenai/Mahou-1.2-llama3-8B
model-index:
  - name: llama-3-NeuralMahou
    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: 67.41
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
          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: 83.45
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
          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: 68.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
          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: 58.21
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
          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: 77.74
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
          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: 72.55
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
          name: Open LLM Leaderboard

NeuralMahou

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mlabonne/NeuralDaredevil-8B-abliterated as a base.

Models Merged

The following models were included in the merge:

• nbeerbower/llama-3-spicy-abliterated-stella-8B
• flammenai/Mahou-1.2-llama3-8B

Configuration

The following YAML configuration was used to produce this model:

base_model: mlabonne/NeuralDaredevil-8B-abliterated
dtype: bfloat16
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 32]
    model: flammenai/Mahou-1.2-llama3-8B
  - layer_range: [0, 32]
    model: nbeerbower/llama-3-spicy-abliterated-stella-8B
  - layer_range: [0, 32]
    model: mlabonne/NeuralDaredevil-8B-abliterated

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.33
AI2 Reasoning Challenge (25-Shot)	67.41
HellaSwag (10-Shot)	83.45
MMLU (5-Shot)	68.63
TruthfulQA (0-shot)	58.21
Winogrande (5-shot)	77.74
GSM8k (5-shot)	72.55