gemma-3-270m-cpt-spm-2K-5y-merged-task_arithmetic

gemma-3-270m-cpt-spm-2K-5y-merged-task_arithmetic

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using rafurafu/gemma-3-270m-cpt-spm-2K-5y as a base.

Models Merged

The following models were included in the merge:

• google/gemma-3-270m

Configuration

The following YAML configuration was used to produce this model:

base_model: rafurafu/gemma-3-270m-cpt-spm-2K-5y
dtype: bfloat16
merge_method: task_arithmetic
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 18]
        model: google/gemma-3-270m
        parameters:
          weight: 0.5
      - layer_range: [0, 18]
        model: rafurafu/gemma-3-270m-cpt-spm-2K-5y
tokenizer:
  source: base