Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper
•
2203.05482
•
Published
•
7
hybrid_play_32b
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:
- StephenZhu/SWE-Play-32B-mix
- synthetic-code-training/qwen25-coder-32b-loc2291-func1907-gen1287-5e-0-00005lr-bs16-bf16
Configuration
The following YAML configuration was used to produce this model:
models:
- model: synthetic-code-training/qwen25-coder-32b-loc2291-func1907-gen1287-5e-0-00005lr-bs16-bf16
parameters:
weight: 0.5
- model: StephenZhu/SWE-Play-32B-mix
parameters:
weight: 0.5
merge_method: linear
dtype: bfloat16
- Downloads last month
- 3
Model tree for synthetic-code-training/hybrid_play_32b
Merge model
this model