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: jeiku/Smort_3B+jeiku/Theory_of_Mind_RP_128_StableLM
parameters:
weight: 1
- model: jeiku/Smort_3B+jeiku/Bluemoon_cleaned_StableLM
parameters:
weight: 1
- model: jeiku/Smort_3B+jeiku/Humiliation_StableLM
parameters:
weight: 1
- model: jeiku/Smort_3B+jeiku/Erotica_StableLM
parameters:
weight: 1
merge_method: linear
dtype: float16
2-bit
6-bit
16-bit