Triangle104/DS-R1-Llama-8B-Harmony

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• deepseek-ai/DeepSeek-R1-Distill-Llama-8B
• huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
        layer_range: [0, 32]
      - model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
        layer_range: [0, 32]
merge_method: slerp
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.57
IFEval (0-Shot)	35.66
BBH (3-Shot)	17.50
MATH Lvl 5 (4-Shot)	33.16
GPQA (0-shot)	5.59
MuSR (0-shot)	6.12
MMLU-PRO (5-shot)	19.37