README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - djuna/ReWiz-Llama-3.2-3B-fix-config
  - SicariusSicariiStuff/Impish_LLAMA_3B
  - unsloth/Llama-3.2-3B
model-index:
  - name: TEST-L3.2-ReWish-3B
    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: 63.68
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B
          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: 22.07
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B
          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: 12.92
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B
          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: 4.47
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B
          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: 7.92
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B
          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: 23.62
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B
          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 linear DARE merge method using unsloth/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

• djuna/ReWiz-Llama-3.2-3B-fix-config
• SicariusSicariiStuff/Impish_LLAMA_3B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/Llama-3.2-3B
  - model: SicariusSicariiStuff/Impish_LLAMA_3B
    parameters:
      weight: 1
  - model: djuna/ReWiz-Llama-3.2-3B-fix-config
    parameters:
      weight: 1
merge_method: dare_linear
base_model: unsloth/Llama-3.2-3B
tokenizer_source: djuna/ReWiz-Llama-3.2-3B-fix-config
parameters:
  normalize: true
  int8_mask: true
dtype: float32
name: rewish

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	22.45
IFEval (0-Shot)	63.68
BBH (3-Shot)	22.07
MATH Lvl 5 (4-Shot)	12.92
GPQA (0-shot)	4.47
MuSR (0-shot)	7.92
MMLU-PRO (5-shot)	23.62