Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper
• 2203.05482 • Published
• 7
This is a merge of pre-trained language models created using mergekit.
This model was merged using the linear merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: MotherEarth/MotherEarth-Proverbs-1.0-8B
parameters:
weight: 1.0
- model: MotherEarth/storm_climate
parameters:
weight: 0.2
- model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated
parameters:
weight: 0.1
- model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
parameters:
weight: 0.1
merge_method: linear
dtype: float16