---
base_model:
- SvalTek/Qwen2.5-ColdBrew-Erratik-test
- fblgit/cybertron-v4-qw7B-UNAMGS
- FuseAI/FuseChat-Qwen-2.5-7B-Instruct
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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [SvalTek/Qwen2.5-ColdBrew-Erratik-test](https://huggingface.co/SvalTek/Qwen2.5-ColdBrew-Erratik-test) as a base.

### Models Merged

The following models were included in the merge:
* [fblgit/cybertron-v4-qw7B-UNAMGS](https://huggingface.co/fblgit/cybertron-v4-qw7B-UNAMGS)
* [FuseAI/FuseChat-Qwen-2.5-7B-Instruct](https://huggingface.co/FuseAI/FuseChat-Qwen-2.5-7B-Instruct)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
name: Qwen2.5-ColdBrew
models:
  - model: SvalTek/Qwen2.5-ColdBrew-Erratik-test
    parameters:
      density: 0.8
      weight: 0.5
  - model: fblgit/cybertron-v4-qw7B-UNAMGS
    parameters:
      density: 0.5
      weight: 0.3
  - model: FuseAI/FuseChat-Qwen-2.5-7B-Instruct
    parameters:
      density: 0.5
      weight: 0.3
merge_method: dare_ties
base_model: SvalTek/Qwen2.5-ColdBrew-Erratik-test
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```