README.md

metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - merge
model-index:
  - name: Mayonnaise-4in1-022
    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: 72.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-022
          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: 88.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-022
          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: 64.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-022
          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: 71.73
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-022
          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: 84.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-022
          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: 70.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Mayonnaise-4in1-022
          name: Open LLM Leaderboard

Warning: This model is ranked first on the Open LLM Leaderboard (among the 7B models) (January 28th, 2024). However, note that this model was produced from many merges. I didn't fine-tune any of the models that I merged and I couldn't confirm that none of them have been trained on the evaluation benchmarks.

Model Card for Model ID

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

Model Details

Model Description

• Developed by: The Kaitchup
• Model type: Causal
• Language(s) (NLP): English
• License: Apache 2.0

Model Sources

Created with mergekit with this configuration:

models:
  - model: mncai/mistral-7b-dpo-v5
    # no parameters necessary for base model
  - model: FelixChao/WestSeverus-7B-DPO-v2
    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.	75.56
AI2 Reasoning Challenge (25-Shot)	72.87
HellaSwag (10-Shot)	88.63
MMLU (5-Shot)	64.93
TruthfulQA (0-shot)	71.73
Winogrande (5-shot)	84.69
GSM8k (5-shot)	70.51