README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - IlyaGusev/gemma-2-9b-it-abliterated
  - crestf411/gemstone-9b
  - BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
  - lemon07r/Gemma-2-Ataraxy-9B
model-index:
  - name: Gemma-2-gemmama-9b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 77.03
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Gemma-2-gemmama-9b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 32.92
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Gemma-2-gemmama-9b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 0
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Gemma-2-gemmama-9b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 11.41
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Gemma-2-gemmama-9b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 8.46
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Gemma-2-gemmama-9b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 23.44
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Gemma-2-gemmama-9b
          name: Open LLM Leaderboard

merge

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 IlyaGusev/gemma-2-9b-it-abliterated as a base.

Models Merged

The following models were included in the merge:

• crestf411/gemstone-9b
• BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
• lemon07r/Gemma-2-Ataraxy-9B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: IlyaGusev/gemma-2-9b-it-abliterated
    #no parameters necessary for base model
  - model: BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
    parameters:
      density: 0.6
      weight: 0.25
  - model: lemon07r/Gemma-2-Ataraxy-9B
    parameters:
      density: 0.4
      weight: 0.3
  - model: crestf411/gemstone-9b
    parameters:
      density: 0.4
      weight: 0.2
merge_method: dare_ties
base_model: IlyaGusev/gemma-2-9b-it-abliterated
parameters:
  normalize: false
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.54
IFEval (0-Shot)	77.03
BBH (3-Shot)	32.92
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	11.41
MuSR (0-shot)	8.46
MMLU-PRO (5-shot)	23.44