Mayonnaise-4in1-02 / README.md
bnjmnmarie's picture
Update README.md
15d0bfe verified
metadata
language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - merge
model-index:
  - name: Mayonnaise-4in1-02
    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: 73.38
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-02
          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: 88.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-02
          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: 64.89
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-02
          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: 69.04
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-02
          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: 84.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-02
          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: 71.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-02
          name: Open LLM Leaderboard

Model Card for Model ID

This is a mixture of experts created with mergekit and based on mistralai/Mistral-7B-v0.1.

Model Details

The model was created using a recipe detailed in this article: The Mayonnaise: Rank First on the Open LLM Leaderboard with TIES-Merging

Model Description

Model Sources

Created with mergekit with this configuration:

models:
  - model: mncai/mistral-7b-dpo-v5
    # no parameters necessary for base model
  - model: flemmingmiguel/MBX-7B
    parameters:
      density: 0.5
      weight: 0.3
  - model: BarryFutureman/NeuralTurdusVariant1-7B
    parameters:
      density: 0.5
      weight: 0.5
merge_method: ties
base_model: mncai/mistral-7b-dpo-v5
parameters:
  normalize: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 75.21
AI2 Reasoning Challenge (25-Shot) 73.38
HellaSwag (10-Shot) 88.51
MMLU (5-Shot) 64.89
TruthfulQA (0-shot) 69.04
Winogrande (5-shot) 84.37
GSM8k (5-shot) 71.04