---
base_model:
- suayptalha/HomerCreativeAnvita-Mix-Qw7B
- AXCXEPT/Qwen2.5-Math-7B-Instruct-jp-EZO_OREO
- SousiOmine/Kuroiso-CR-7B-20250124
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 [SousiOmine/Kuroiso-CR-7B-20250124](https://huggingface.co/SousiOmine/Kuroiso-CR-7B-20250124) as a base.

### Models Merged

The following models were included in the merge:
* [suayptalha/HomerCreativeAnvita-Mix-Qw7B](https://huggingface.co/suayptalha/HomerCreativeAnvita-Mix-Qw7B)
* [AXCXEPT/Qwen2.5-Math-7B-Instruct-jp-EZO_OREO](https://huggingface.co/AXCXEPT/Qwen2.5-Math-7B-Instruct-jp-EZO_OREO)

### Configuration

The following YAML configuration was used to produce this model:

```yaml


models:
  - model: suayptalha/HomerCreativeAnvita-Mix-Qw7B
    parameters:
      weight: 1
      density: 1
  - model: AXCXEPT/Qwen2.5-Math-7B-Instruct-jp-EZO_OREO
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: SousiOmine/Kuroiso-CR-7B-20250124
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: float16

```