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 Theros/Qwen2.5-ColdBrew-R1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
name: SvalTek/Qwen2.5-ColdBrew-Erratik
models:
- model: SvalTek/Qwen2.5-ColdBrew-Solipsis
- model: Theros/Qwen2.5-ColdBrew-R1
- model: Theros/Qwen2.5-CreativeMix-7B
- model: Theros/Qwen2.5-CyberMix-7B
merge_method: model_stock
base_model: Theros/Qwen2.5-ColdBrew-R1
parameters:
int8_mask: true
dtype: bfloat16