Modelpublic

DreadPoor/BaeZel-8B-LINEAR

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

1likes44downloads

Model Card

merge

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

image/png

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

—DreadPoor/Heart_Stolen-8B-Model_Stock
—DreadPoor/Aspire_1.3-8B_model-stock
—DreadPoor/LemonP-8B-Model_Stock

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: DreadPoor/Aspire_1.3-8B_model-stock
    parameters:
      weight: 1.0
  - model: DreadPoor/LemonP-8B-Model_Stock
    parameters:
      weight: 1.0
  - model: DreadPoor/Heart_Stolen-8B-Model_Stock
    parameters:
      weight: 1.0
merge_method: linear
normalize: false
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	30.30
IFEval (0-Shot)	73.78
BBH (3-Shot)	35.54
MATH Lvl 5 (4-Shot)	17.82
GPQA (0-shot)	9.51
MuSR (0-shot)	13.34
MMLU-PRO (5-shot)	31.79