Editing Models with Task Arithmetic
Paper
•
2212.04089
•
Published
•
7
This is a merge of pre-trained language models created using mergekit.
Experimental component for a project. Extremely dumb config that I expect to have to tune. Mostly effective, but a bit dumb because the regular projection-ablit is the dumbest one.
This model was merged using the Task Arithmetic merge method using grimjim/gemma-3-12b-it-projection-abliterated as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: TheDrummer/Tiger-Gemma-12B-v3
parameters:
weight: 1
- model: soob3123/Veiled-Calla-12B
parameters:
weight: 1
merge_method: task_arithmetic
base_model: grimjim/gemma-3-12b-it-projection-abliterated
parameters:
normalize: true