Modelpublic

sequelbox/gemma-4-12B-it-Esper4Tachibana

sourceHugging Faceupdated 2mo agoView on Hugging Face

0likes5downloads

Model Card

Esper4Tachibana12b

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:

—ValiantLabs/gemma-4-12B-it-Esper4
—sequelbox/gemma-4-12B-it-Tachibana-Agent

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: dare_ties
dtype: bfloat16
parameters:
  normalize: true
tokenizer:
  source: "base"
models:
  - model: ValiantLabs/gemma-4-12B-it-Esper4
    parameters:
      density: 0.5
      weight: 0.8
  - model: sequelbox/gemma-4-12B-it-Tachibana-Agent
    parameters:
      density: 0.5
      weight: 0.8
base_model: google/gemma-4-12B-it