README.md

metadata

language:
  - en
license: openrail
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - SanjiWatsuki/Sonya-7B
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
  - SanjiWatsuki/Kunoichi-7B
pipeline_tag: text-generation
model-index:
  - name: Mistral_Sonyichi-7B-slerp
    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: 67.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
          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: 86.43
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
          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: 63.58
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
          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: 63.25
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
          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: 78.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
          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: 63.84
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
          name: Open LLM Leaderboard

merged

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• SanjiWatsuki/Sonya-7B
• EmbeddedLLM/Mistral-7B-Merge-14-v0.1
• SanjiWatsuki/Kunoichi-7B

Configuration

The following YAML configuration was used to produce this model:

base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 32]
    model: SanjiWatsuki/Sonya-7B
  - layer_range: [0, 32]
    model: SanjiWatsuki/Kunoichi-7B

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.52
AI2 Reasoning Challenge (25-Shot)	67.49
HellaSwag (10-Shot)	86.43
MMLU (5-Shot)	63.58
TruthfulQA (0-shot)	63.25
Winogrande (5-shot)	78.53
GSM8k (5-shot)	63.84