---
base_model:
- Theros/Qwen2.5-CyberMix-7B
- bunnycore/Qwen-2.5-7B-Deep-Stock-v4
- Theros/Qwen2.5-ColdBrew-R1-test8
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Theros/Qwen2.5-ColdBrew-R1-test8](https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1-test8) as a base.

### Models Merged

The following models were included in the merge:
* [Theros/Qwen2.5-CyberMix-7B](https://huggingface.co/Theros/Qwen2.5-CyberMix-7B)
* [bunnycore/Qwen-2.5-7B-Deep-Stock-v4](https://huggingface.co/bunnycore/Qwen-2.5-7B-Deep-Stock-v4)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Theros/Qwen2.5-ColdBrew-R1-test8
  - model: Theros/Qwen2.5-CyberMix-7B
  - model: bunnycore/Qwen-2.5-7B-Deep-Stock-v4
merge_method: model_stock
base_model: Theros/Qwen2.5-ColdBrew-R1-test8
normalize: true
int8_mask: true
dtype: bfloat16
tokenizer_source: Theros/Qwen2.5-ColdBrew-R1-test8
```