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: Qwen/Qwen2.5-Math-1.5B-Instruct
parameters:
weight: 0.5
- model: ../../skywork-o1-prm-inference/new_model_path
parameters:
weight: 0.5
merge_method: linear
dtype: float16
Base model
Qwen/Qwen2.5-1.5B