README.md

---
base_model:
- AXCXEPT/EZO-Humanities-9B-gemma-2-it
- IlyaGusev/gemma-2-9b-it-abliterated
- AXCXEPT/EZO-Common-9B-gemma-2-it
- lemon07r/Gemma-2-Ataraxy-v4d-9B
library_name: transformers
tags:
- mergekit
- merge

---
![image/png](https://huggingface.co/yamatazen/Irida-SCE-9B/resolve/main/Irida-SCE-9B.png?download=true)

# 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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [IlyaGusev/gemma-2-9b-it-abliterated](https://huggingface.co/IlyaGusev/gemma-2-9b-it-abliterated) as a base.

### Models Merged

The following models were included in the merge:
* [AXCXEPT/EZO-Humanities-9B-gemma-2-it](https://huggingface.co/AXCXEPT/EZO-Humanities-9B-gemma-2-it)
* [AXCXEPT/EZO-Common-9B-gemma-2-it](https://huggingface.co/AXCXEPT/EZO-Common-9B-gemma-2-it)
* [lemon07r/Gemma-2-Ataraxy-v4d-9B](https://huggingface.co/lemon07r/Gemma-2-Ataraxy-v4d-9B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: IlyaGusev/gemma-2-9b-it-abliterated
models:
  - model: lemon07r/Gemma-2-Ataraxy-v4d-9B
  - model: AXCXEPT/EZO-Common-9B-gemma-2-it
  - model: AXCXEPT/EZO-Humanities-9B-gemma-2-it
merge_method: sce
dtype: bfloat16
parameters:
  normalize: true
  select_topk: 0.5
```