Editing Models with Task Arithmetic
Paper
• 2212.04089 • Published
• 7
This is a merge of pre-trained language models created using mergekit.
This model was merged using the task arithmetic merge method using NewEden/nemo-erebus as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: anthracite-org/magnum-v2.5-12b-kto
parameters:
density: 0.2
weight: 0.53
- model: nbeerbower/mistral-nemo-gutenberg-12B-v4
parameters:
density: 0.2
weight: 0.53
- model: TheDrummer/UnslopNemo-12B-v4.1
parameters:
density: 0.5
weight: 0.53
merge_method: task_arithmetic
base_model: NewEden/nemo-erebus
parameters:
normalize: false
int8_mask: true
dtype: bfloat16