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: overfit-brothers/hello_world06
parameters:
weight: 0.4
- model: Q-PING/krx_1205_test_model_3
parameters:
weight: 0.3
- model: Hi-Q/krx_1206_test_model_2
parameters:
weight: 0.3
merge_method: linear
dtype: bfloat16