Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper
• 2203.05482 • Published
• 7
negative-confetti
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: ToastyPigeon/gemma3-27b-v2-confettilike
parameters:
weight: -0.5
- model: google/gemma-3-27b-pt
parameters:
weight: 1.5
merge_method: linear
dtype: bfloat16
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ToastyPigeon/negative-confetti
Merge model
this model