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 Test157t/Pasta-PrimaMaid-7b as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: task_arithmetic
base_model: Test157t/Pasta-PrimaMaid-7b
parameters:
normalize: true
models:
- model: Test157t/Pasta-PrimaMaid-7b+jeiku/Theory_of_Mind_Roleplay_Mistral
parameters:
weight: 0.5
- model: Test157t/Pasta-PrimaMaid-7b+jeiku/Theory_of_Mind_Mistral
parameters:
weight: 0.65
- model: Test157t/Pasta-PrimaMaid-7b+jeiku/Gnosis_Reformatted_Mistral
parameters:
weight: 0.75
- model: Test157t/Pasta-PrimaMaid-7b+jeiku/Futadom_Mistral
parameters:
weight: 0.8
- model: Test157t/Pasta-PrimaMaid-7b+jeiku/Humiliation_Mistral
parameters:
weight: 0.6
dtype: float16