metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - nbeerbower/gemma2-gutenberg-9B
  - princeton-nlp/gemma-2-9b-it-SimPO
  - jsgreenawalt/gemma-2-9B-it-advanced-v2.1
  - UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
  - recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
  - unsloth/gemma-2-9b-it
  - lemon07r/Gemma-2-Ataraxy-v2-9B
  - ifable/gemma-2-Ifable-9B
  - grimjim/Gemma2-Nephilim-v3-9B
  - lemon07r/Gemma-2-Ataraxy-v2a-9B
  - wzhouad/gemma-2-9b-it-WPO-HB
  - lemon07r/Gemma-2-Ataraxy-9B
model-index:
  - name: Gemma-2-Ataraxy-Remix-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: 70.83
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-Remix-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: 41.59
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-Remix-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: 1.28
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-Remix-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: 11.86
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-Remix-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: 13.72
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-Remix-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: 35.99
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-Remix-9B
          name: Open LLM Leaderboard

Gemma-2-Ataraxy-Remix-9B-Q8_0-GGUF

This is the Q8_0 GGUF for people to try while I evaluate my merges.

Another test model. Ignore this for now. Probably wont be good but I am testing a lot of stuff.

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 unsloth/gemma-2-9b-it as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: unsloth/gemma-2-9b-it
dtype: bfloat16
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 42]
    model: lemon07r/Gemma-2-Ataraxy-9B
  - layer_range: [0, 42]
    model: lemon07r/Gemma-2-Ataraxy-v2-9B
  - layer_range: [0, 42]
    model: lemon07r/Gemma-2-Ataraxy-v2a-9B
  - layer_range: [0, 42]
    model: jsgreenawalt/gemma-2-9B-it-advanced-v2.1
  - layer_range: [0, 42]
    model: ifable/gemma-2-Ifable-9B
  - layer_range: [0, 42]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
  - layer_range: [0, 42]
    model: princeton-nlp/gemma-2-9b-it-SimPO
  - layer_range: [0, 42]
    model: wzhouad/gemma-2-9b-it-WPO-HB
  - layer_range: [0, 42]
    model: nbeerbower/gemma2-gutenberg-9B
  - layer_range: [0, 42]
    model: grimjim/Gemma2-Nephilim-v3-9B
  - layer_range: [0, 42]
    model: recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
  - layer_range: [0, 42]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
  - layer_range: [0, 42]
    model: unsloth/gemma-2-9b-it

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.21
IFEval (0-Shot)	70.83
BBH (3-Shot)	41.59
MATH Lvl 5 (4-Shot)	1.28
GPQA (0-shot)	11.86
MuSR (0-shot)	13.72
MMLU-PRO (5-shot)	35.99