README.md

metadata

license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - elinas/Chronos-Gold-12B-1.0
  - nbeerbower/mistral-nemo-gutenberg3-12B
  - crestf411/MN-Slush
  - nothingiisreal/MN-12B-Celeste-V1.9
  - Gryphe/Pantheon-RP-1.6.1-12b-Nemo
  - anthracite-org/magnum-v4-12b
model-index:
  - name: Annunaki-12b
    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: 38.72
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
          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: 35.32
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
          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: 11.33
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
          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: 9.51
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
          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: 14.28
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
          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: 30.23
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
          name: Open LLM Leaderboard

Merge

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

Merge Details

A merge of some of my fave Mistral Nemo models.

Quant: https://huggingface.co/Triangle104/Annunaki-12b-Q4_K_M-GGUF

Merge Method

This model was merged using the Model Stock merge method using nothingiisreal/MN-12B-Celeste-V1.9 as a base.

Models Merged

The following models were included in the merge:

• elinas/Chronos-Gold-12B-1.0
• nbeerbower/mistral-nemo-gutenberg3-12B
• crestf411/MN-Slush
• Gryphe/Pantheon-RP-1.6.1-12b-Nemo
• anthracite-org/magnum-v4-12b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: crestf411/MN-Slush
  - model: elinas/Chronos-Gold-12B-1.0
  - model: nbeerbower/mistral-nemo-gutenberg3-12B
  - model: nothingiisreal/MN-12B-Celeste-V1.9
  - model: anthracite-org/magnum-v4-12b
  - model: Gryphe/Pantheon-RP-1.6.1-12b-Nemo
base_model: nothingiisreal/MN-12B-Celeste-V1.9
merge_method: model_stock
parameters:
  normalize: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	23.23
IFEval (0-Shot)	38.72
BBH (3-Shot)	35.32
MATH Lvl 5 (4-Shot)	11.33
GPQA (0-shot)	9.51
MuSR (0-shot)	14.28
MMLU-PRO (5-shot)	30.23