Editing Models with Task Arithmetic
Paper • 2212.04089 • Published • 8
This is a merge of pre-trained language models created using mergekit.
This model was merged using the task arithmetic merge method using NousResearch/Hermes-2-Theta-Llama-3-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: NousResearch/Hermes-2-Theta-Llama-3-8B
- model: mlabonne/NeuralDaredevil-8B-abliterated
parameters:
weight: 0.45
base_model: NousResearch/Hermes-2-Theta-Llama-3-8B
merge_method: task_arithmetic
dtype: bfloat16