README.md

metadata

license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - flammenai/Mahou-1.5-mistral-nemo-12B
  - nbeerbower/Mistral-Nemo-12B-abliterated-LORA
model-index:
  - name: Mahou-1.5-mistral-nemo-12B-lorablated
    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: 68.25
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
          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: 36.08
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
          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: 5.29
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
          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: 3.91
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
          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: 16.55
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
          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: 28.6
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
          name: Open LLM Leaderboard

Mahou-1.5-mistral-nemo-12B-lorablated

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using flammenai/Mahou-1.5-mistral-nemo-12B + nbeerbower/Mistral-Nemo-12B-abliterated-LORA 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: flammenai/Mahou-1.5-mistral-nemo-12B+nbeerbower/Mistral-Nemo-12B-abliterated-LORA
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 40]
    model: flammenai/Mahou-1.5-mistral-nemo-12B+nbeerbower/Mistral-Nemo-12B-abliterated-LORA
    parameters:
      weight: 1.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.45
IFEval (0-Shot)	68.25
BBH (3-Shot)	36.08
MATH Lvl 5 (4-Shot)	5.29
GPQA (0-shot)	3.91
MuSR (0-shot)	16.55
MMLU-PRO (5-shot)	28.60