Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using SvalTek/Qwen2.5-ColdBrew as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: SvalTek/Qwen2.5-ColdBrew
- model: fblgit/cybertron-v4-qw7B-UNAMGS
parameters:
weight: 0.4
- model: bunnycore/Qwen-2.5-7B-R1-Stock
parameters:
weight: 0.4
base_model: SvalTek/Qwen2.5-ColdBrew
merge_method: model_stock
parameters:
dtype: bfloat16
tokenizer_source: SvalTek/Qwen2.5-ColdBrew