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:
merge_method: linear
dtype: float16
models:
- model: teknium/OpenHermes-2.5-Mistral-7B
parameters:
weight: 1.0
- model: Open-Orca/Mistral-7B-SlimOrca
parameters:
weight: 1.0
#tokenizer_source: union