metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - DavidAU/Gemma-The-Writer-Mighty-Sword-9B
  - Rombo-Org/Rombo-LLM-V2.7-gemma-2-9b
  - TheDrummer/Gemmasutra-9B-v1.1
  - anthracite-org/magnum-v4-9b
  - nbeerbower/Gemma2-Gutenberg-Doppel-9B
  - allura-org/G2-9B-Aletheia-v1
model-index:
  - name: Gemmadevi-Stock-10B
    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: 15.82
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Gemmadevi-Stock-10B
          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: 43.62
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Gemmadevi-Stock-10B
          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: 2.79
            name: exact match
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Gemmadevi-Stock-10B
          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: 13.76
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Gemmadevi-Stock-10B
          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: 17.23
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Gemmadevi-Stock-10B
          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: 36.24
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Gemmadevi-Stock-10B
          name: Open LLM Leaderboard

Merge

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

Merge Method

This model was merged using the Model Stock merge method using TheDrummer/Gemmasutra-9B-v1.1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/Gemmasutra-9B-v1.1
  - model: Rombo-Org/Rombo-LLM-V2.7-gemma-2-9b
  - model: allura-org/G2-9B-Aletheia-v1
  - model: anthracite-org/magnum-v4-9b
  - model: nbeerbower/Gemma2-Gutenberg-Doppel-9B
  - model: DavidAU/Gemma-The-Writer-Mighty-Sword-9B
merge_method: model_stock
base_model: TheDrummer/Gemmasutra-9B-v1.1
parameters:
    normalize: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.58
IFEval (0-Shot)	15.82
BBH (3-Shot)	43.62
MATH Lvl 5 (4-Shot)	2.79
GPQA (0-shot)	13.76
MuSR (0-shot)	17.23
MMLU-PRO (5-shot)	36.24