---
base_model:
- AXCXEPT/EZO-Humanities-9B-gemma-2-it
- mergekit-community/Tigers-Abliterated-9B
- crestf411/gemma2-9B-sunfall-v0.5.2
- gmonsoon/SahabatAI-Lion-9B-TIES-v1
- allura-org/G2-9B-Aletheia-v1
- AXCXEPT/EZO-Common-9B-gemma-2-it
- lemon07r/Gemma-2-Ataraxy-v4d-9B
library_name: transformers
tags:
- mergekit
- merge
language:
- en
- ja
---
![image/png](https://huggingface.co/yamatazen/Gemma2-Snowflakes-9B/resolve/main/Gemma2-Snowflake-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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [mergekit-community/Tigers-Abliterated-9B](https://huggingface.co/mergekit-community/Tigers-Abliterated-9B) 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)
* [crestf411/gemma2-9B-sunfall-v0.5.2](https://huggingface.co/crestf411/gemma2-9B-sunfall-v0.5.2)
* [gmonsoon/SahabatAI-Lion-9B-TIES-v1](https://huggingface.co/gmonsoon/SahabatAI-Lion-9B-TIES-v1)
* [allura-org/G2-9B-Aletheia-v1](https://huggingface.co/allura-org/G2-9B-Aletheia-v1)
* [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: mergekit-community/Tigers-Abliterated-9B
models:
  - model: lemon07r/Gemma-2-Ataraxy-v4d-9B
    parameters:
      density: 0.75
      weight: 1.0
  - model: allura-org/G2-9B-Aletheia-v1
    parameters:
      density: 0.6
      weight: 0.8
  - model: AXCXEPT/EZO-Common-9B-gemma-2-it
    parameters:
      density: 0.5
      weight: 0.5
  - model: AXCXEPT/EZO-Humanities-9B-gemma-2-it
    parameters:
      density: 0.5
      weight: 0.5
  - model: crestf411/gemma2-9B-sunfall-v0.5.2
    parameters:
      density: 0.3
      weight: 0.3
  - model: gmonsoon/SahabatAI-Lion-9B-TIES-v1
    parameters:
      density: 0.3
      weight: 0.3
merge_method: ties
dtype: bfloat16
parameters:
  normalize: true
```