Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 8
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Linear merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: BioMistral/BioMistral-7B
parameters:
weight: 1.0
- model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
weight: 0.3
- model: BioMistral/BioMistral-7B
parameters:
weight: 0.5
merge_method: linear
dtype: float16
- Downloads last month
- 2