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: models/llm-jp-1.3b-1
parameters:
weight: 0.7
- model: models/llm-jp-1.3b-2
parameters:
weight: 0.3
merge_method: linear
dtype: float16