Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 8
llama3-1b-linear-v1
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:
dtype: float16
merge_method: linear
modules:
default:
slices:
- sources:
- layer_range: [0, 16]
model: Alelcv27/llama3-1b-code-dpo
parameters:
weight: 0.5
- layer_range: [0, 16]
model: Alelcv27/llama3-1b-math-dpo
parameters:
weight: 0.5
- Downloads last month
- 1