This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Task Arithmetic merge method using
google/gemma-3-1b-pt as a base.
1base_model: google/gemma-3-1b-pt
2merge_method: task_arithmetic
3modules:
4 default:
5 slices:
6 - sources:
7 - layer_range: [0, 26]
8 model: TheMockingJay1013/gemma-3-sft
9 parameters:
10 weight: 1.0
11 - layer_range: [0, 26]
12 model: TheMockingJay1013/gemma-3-safe
13 parameters:
14 weight: 1.0
15 - layer_range: [0, 26]
16 model: google/gemma-3-1b-pt
