metadata

language:
  - en
license: llama3.2
library_name: transformers
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3
  - mergekit
  - merge
  - chat
  - moonride
base_model:
  - meta-llama/Llama-3.2-3B
  - bunnycore/Llama-3.2-3B-Mix-Skill
  - bunnycore/Llama-3.2-3B-Sci-Think
  - FuseAI/FuseChat-Llama-3.2-3B-Instruct
  - theprint/ReWiz-Llama-3.2-3B
pipeline_tag: text-generation
model-index:
  - name: Llama-3.2-3B-Khelavaster
    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: 49.25
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
          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: 22.69
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
          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: 16.16
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
          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: 3.69
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
          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: 5.5
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
          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: 23.57
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
          name: Open LLM Leaderboard

Intro

Experimental merge of multiple Llama 3.2 3B models, guided by MoonRide-Index-v7. Created with mergekit.

Merge Details

Merge Method

This model was merged using the SCE merge method using meta-llama/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Llama-3.2-3B-Mix-Skill
  - model: bunnycore/Llama-3.2-3B-Sci-Think
  - model: FuseAI/FuseChat-Llama-3.2-3B-Instruct
  - model: theprint/ReWiz-Llama-3.2-3B
base_model: meta-llama/Llama-3.2-3B
tokenizer:
  source: meta-llama/Llama-3.2-3B-Instruct
merge_method: sce
parameters:
  normalize: true
dtype: float32
out_dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	20.14
IFEval (0-Shot)	49.25
BBH (3-Shot)	22.69
MATH Lvl 5 (4-Shot)	16.16
GPQA (0-shot)	3.69
MuSR (0-shot)	5.50
MMLU-PRO (5-shot)	23.57