README.md

metadata

license: apache-2.0
tags:
  - mergekit
  - merge
base_model:
  - openchat/openchat-3.5-0106
  - mistralai/Mistral-7B-Instruct-v0.2
  - Open-Orca/Mistral-7B-OpenOrca
  - WizardLM/WizardMath-7B-V1.1
model-index:
  - name: DARE-Merging
    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: 25.26
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
          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: 26.11
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
          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: 23.68
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
          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: 48.31
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
          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: 51.7
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
          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: 0.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
          name: Open LLM Leaderboard

result

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mistralai/Mistral-7B-Instruct-v0.2 as a base.

Models Merged

The following models were included in the merge:

• openchat/openchat-3.5-0106
• Open-Orca/Mistral-7B-OpenOrca
• WizardLM/WizardMath-7B-V1.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # No parameters necessary for base model
  - model: Open-Orca/Mistral-7B-OpenOrca
    parameters:
      density: 0.5
      weight: 0.3
  - model: openchat/openchat-3.5-0106
    parameters:
      density: 0.5
      weight: 0.3
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.5
      weight: 0.3
merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
  normalize: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.19
AI2 Reasoning Challenge (25-Shot)	25.26
HellaSwag (10-Shot)	26.11
MMLU (5-Shot)	23.68
TruthfulQA (0-shot)	48.31
Winogrande (5-shot)	51.70
GSM8k (5-shot)	0.08