README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - unsloth/gemma-2-27b-it
  - AALF/gemma-2-27b-it-SimPO-37K-100steps
  - djuna/G2-BigGSHT-27B-calc
model-index:
  - name: G2-BigGSHT-27B-2
    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: 79.74
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-BigGSHT-27B-2
          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: 48.81
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-BigGSHT-27B-2
          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/G2-BigGSHT-27B-2
          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: 15.1
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-BigGSHT-27B-2
          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: 9.93
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-BigGSHT-27B-2
          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: 39.2
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-BigGSHT-27B-2
          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 Model Stock merge method using AALF/gemma-2-27b-it-SimPO-37K-100steps as a base.

Models Merged

The following models were included in the merge:

• unsloth/gemma-2-27b-it
• djuna/G2-BigGSHT-27B-calc

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: djuna/G2-BigGSHT-27B-calc
  - model: unsloth/gemma-2-27b-it
merge_method: model_stock
base_model: AALF/gemma-2-27b-it-SimPO-37K-100steps
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	32.13
IFEval (0-Shot)	79.74
BBH (3-Shot)	48.81
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	15.10
MuSR (0-shot)	9.93
MMLU-PRO (5-shot)	39.20