Modelpublic

djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc

sourceHugging Faceupdated 2y agoView on Hugging Face

2likes35downloads

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 della merge method using unsloth/Meta-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: DreadPoor/Aspire1.1-8B-model_stock
    parameters:
      weight: 1.0
  - model: DreadPoor/Spei_Meridiem-8B-model_stock
    parameters:
      weight: 1.0
  - model: DreadPoor/Heart_Stolen1.1-8B-Model_Stock
    parameters:
      weight: 1.0
merge_method: della
base_model: unsloth/Meta-Llama-3.1-8B
parameters:
  density: 1
  lambda: 1.05
  epsilon: 0.04
  normalize: true
  int8_mask: true
dtype: float32
out_dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.18
IFEval (0-Shot)	72.35
BBH (3-Shot)	34.88
MATH Lvl 5 (4-Shot)	13.97
GPQA (0-shot)	8.61
MuSR (0-shot)	13.03
MMLU-PRO (5-shot)	32.26