ties_wjb_9k_subsample

ties

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

Merge Details

Merge Method

This model was merged using the TIES merge method using google/gemma-3-1b-it as a base.

Models Merged

The following models were included in the merge:

• aarnav11/gemma_1b_cares18k
• matheusfarocha/gemini-3-1b-it-wildjailbreak-9k-subsample

Configuration

The following YAML configuration was used to produce this model:

base_model: google/gemma-3-1b-it
dtype: bfloat16
merge_method: ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 26]
        model: aarnav11/gemma_1b_cares18k
        parameters:
          density: 0.5
          weight: 1.0
      - layer_range: [0, 26]
        model: matheusfarocha/gemini-3-1b-it-wildjailbreak-9k-subsample
        parameters:
          density: 0.5
          weight: 1.0
      - layer_range: [0, 26]
        model: google/gemma-3-1b-it
parameters:
  normalize: 1.0