README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - huihui-ai/Llama-3.2-3B-Instruct-abliterated
  - bunnycore/Llama-3.2-3B-CodeReactor
  - bunnycore/Llama-3.2-3B-Mix-Skill
  - bunnycore/Llama-3.2-3B-All-Mix
  - bunnycore/Llama-3.2-3B-ProdigyPlusPlus
  - bunnycore/Llama-3.2-3B-Sci-Think
  - bunnycore/Llama-3.2-3B-Long-Think
  - bunnycore/Llama-3.2-3B-Booval
  - bunnycore/Llama-3.2-3B-ProdigyPlus
  - bunnycore/Llama-3.2-3B-Pure-RP
model-index:
  - name: Llama-3.2-3B-ProdigyPlusPlus
    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: 16.45
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ProdigyPlusPlus
          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: 11.56
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ProdigyPlusPlus
          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: 2.95
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ProdigyPlusPlus
          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: 0.45
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ProdigyPlusPlus
          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: 1.7
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ProdigyPlusPlus
          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: 5.56
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ProdigyPlusPlus
          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 TIES merge method using huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Llama-3.2-3B-CodeReactor
• bunnycore/Llama-3.2-3B-Mix-Skill
• bunnycore/Llama-3.2-3B-All-Mix
• bunnycore/Llama-3.2-3B-ProdigyPlusPlus
• bunnycore/Llama-3.2-3B-Sci-Think
• bunnycore/Llama-3.2-3B-Long-Think
• bunnycore/Llama-3.2-3B-Booval
• bunnycore/Llama-3.2-3B-ProdigyPlus
• bunnycore/Llama-3.2-3B-Pure-RP

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Llama-3.2-3B-Sci-Think
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-CodeReactor
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Long-Think
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Pure-RP
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Booval
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Mix-Skill
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-ProdigyPlus
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-All-Mix
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	6.44
IFEval (0-Shot)	16.45
BBH (3-Shot)	11.56
MATH Lvl 5 (4-Shot)	2.95
GPQA (0-shot)	0.45
MuSR (0-shot)	1.70
MMLU-PRO (5-shot)	5.56