Modelpublic

zelk12/MT1-gemma-2-9B

sourceHugging Faceupdated 2y agoView on Hugging Face

2likes22downloads

Model Card

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:

—zelk12/MT1-GB-gemma-2-9B
—zelk12/MT1-IMMMU-gemma-2-9B

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: zelk12/MT1-GB-gemma-2-9B
  - model: zelk12/MT1-IMMMU-gemma-2-9B
merge_method: slerp
base_model: zelk12/MT1-GB-gemma-2-9B
dtype: bfloat16
parameters:
  t: 0.5

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	33.37
IFEval (0-Shot)	79.47
BBH (3-Shot)	44.16
MATH Lvl 5 (4-Shot)	13.37
GPQA (0-shot)	12.75
MuSR (0-shot)	13.16
MMLU-PRO (5-shot)	37.31