---
base_model:
- prithivMLmods/QwQ-MathOct-7B
- pe-nlp/R1-Qwen2.5-7B-Instruct
- prithivMLmods/Viper-Coder-HybridMini-v1.3
- lkoenig/BBAI_230_Xiaqwen
- Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview](https://huggingface.co/Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview) as a base.

### Models Merged

The following models were included in the merge:
* [prithivMLmods/QwQ-MathOct-7B](https://huggingface.co/prithivMLmods/QwQ-MathOct-7B)
* [pe-nlp/R1-Qwen2.5-7B-Instruct](https://huggingface.co/pe-nlp/R1-Qwen2.5-7B-Instruct)
* [prithivMLmods/Viper-Coder-HybridMini-v1.3](https://huggingface.co/prithivMLmods/Viper-Coder-HybridMini-v1.3)
* [lkoenig/BBAI_230_Xiaqwen](https://huggingface.co/lkoenig/BBAI_230_Xiaqwen)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
    #no parameters necessary for base model
  - model: prithivMLmods/Viper-Coder-HybridMini-v1.3
    parameters:
      density: 0.25
      weight: 0.25
  - model: lkoenig/BBAI_230_Xiaqwen
    parameters:
      density: 0.25
      weight: 0.25
  - model: prithivMLmods/QwQ-MathOct-7B
    parameters:
      density: 0.25
      weight: 0.25
  - model: pe-nlp/R1-Qwen2.5-7B-Instruct
    parameters:
      density: 0.25
      weight: 0.25
# Equal weight and density values for all models (following the OG Dyanka recipe)

merge_method: ties
base_model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
```