bunnycore/Smol-Llama-3.2-3B

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method using huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• passing2961/Thanos-3B
• prithivMLmods/Llama-Sentient-3.2-3B-Instruct
• bunnycore/Llama-3.2-3B-RP-DeepThink
• bunnycore/Llama-3.2-3B-All-Mix
• prithivMLmods/Codepy-Deepthink-3B
• HuggingFaceTB/finemath-ablation-infiwebmath

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
dtype: bfloat16
normalize: true
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
models:
  - model: bunnycore/Llama-3.2-3B-All-Mix
    parameters:
      weight: 10
      density: 1
  - model: prithivMLmods/Codepy-Deepthink-3B
    parameters:
      weight: 7
      density: 0.8
  - model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
    parameters:
      weight: 10
      density: 1
  - model: HuggingFaceTB/finemath-ablation-infiwebmath
    parameters:
      weight: 7
      density: 0.8
  - model: prithivMLmods/Llama-Sentient-3.2-3B-Instruct
    parameters:
      weight: 7
      density: 0.8
  - model: passing2961/Thanos-3B
    parameters:
      weight: 7
      density: 0.8
  - model: bunnycore/Llama-3.2-3B-RP-DeepThink
    parameters:
      weight: 7
      density: 0.8

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	22.47
IFEval (0-Shot)	66.79
BBH (3-Shot)	23.04
MATH Lvl 5 (4-Shot)	13.52
GPQA (0-shot)	3.58
MuSR (0-shot)	3.15
MMLU-PRO (5-shot)	24.76