README.md

---
base_model:
- princeton-nlp/gemma-2-9b-it-SimPO
- lemon07r/Gemma-2-Ataraxy-v2-9B
library_name: transformers
tags:
- mergekit
- merge
language:
- en
---
# Gemma 2 Aeria 9B

This is a merge of pre-trained language models created using [Mergekit](https://github.com/cg123/mergekit).

### Merge Method

This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO) as a base.

### Models Merged

The following models were included in the merge:
* [princeton-nlp/gemma-2-9b-it-SimPO](princeton-nlp/gemma-2-9b-it-SimPO)
* [lemon07r/Gemma-2-Ataraxy-v2-9B](https://huggingface.co/lemon07r/Gemma-2-Ataraxy-v2-9B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: princeton-nlp/gemma-2-9b-it-SimPO
models:
  - model: princeton-nlp/gemma-2-9b-it-SimPO
  - model: lemon07r/Gemma-2-Ataraxy-v2-9B
    parameters:
      density: 0.5
      weight: 1
merge_method: dare_ties
parameters:
  int8_mask: true
chat_template: auto
dtype: bfloat16
```