Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 8
acc0.1fmt0.9
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:
- /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/acc_openrs_8k_kl/global_step_40/actor/huggingface
- /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/binary_openrs_8k_kl/global_step_50/actor/huggingface
Configuration
The following YAML configuration was used to produce this model:
models:
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/acc_openrs_8k_kl/global_step_40/actor/huggingface
parameters:
weight: 0.1
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/binary_openrs_8k_kl/global_step_50/actor/huggingface
parameters:
weight: 0.9
merge_method: linear
parameters:
normalize: true
dtype: bfloat16
- Downloads last month
- 1