TheMockingJay1013/gemma-3-sft-dare

merged

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

Merge Details

Merge Method

This model was merged using the Linear DARE merge method using google/gemma-3-1b-pt as a base.

Models Merged

The following models were included in the merge:

• TheMockingJay1013/gemma-3-sft

Configuration

The following YAML configuration was used to produce this model:

base_model: google/gemma-3-1b-pt
dtype: bfloat16
merge_method: dare_linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 26]
        model: google/gemma-3-1b-pt
        parameters:
          density: 1.0
          weight: 1.0
      - layer_range: [0, 26]
        model: TheMockingJay1013/gemma-3-sft
        parameters:
          density: 1.0
          weight: 1.0
parameters:
  int8_mask: 1.0