Modelpublic

tepirale/gemma-4-12B-merge-coder40-agentic40-it20-dare_ties

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes9downloads

Model Card

merged-gemma4-12b

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using google/gemma-4-12B-it as a base.

Models Merged

The following models were included in the merge:

—tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1
—tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1

Configuration

The following YAML configuration was used to produce this model:

yaml


merge_method: dare_ties
base_model: google/gemma-4-12B-it
dtype: bfloat16
parameters:
  int8_mask: true
models:
  - model: tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1
    parameters:
      weight: 0.40
      density: 0.90
  - model: tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1
    parameters:
      weight: 0.40
      density: 0.90
  - model: google/gemma-4-12B-it
    parameters:
      weight: 0.20
      density: 1.0