README.md

---
base_model:
- unsloth/gemma-3-27b-it
- summykai/gemma3-27b-abliterated-dpo
- mlabonne/gemma-3-27b-it-abliterated
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [unsloth/gemma-3-27b-it](https://huggingface.co/unsloth/gemma-3-27b-it) as a base.

### Models Merged

The following models were included in the merge:
* [summykai/gemma3-27b-abliterated-dpo](https://huggingface.co/summykai/gemma3-27b-abliterated-dpo)
* [mlabonne/gemma-3-27b-it-abliterated](https://huggingface.co/mlabonne/gemma-3-27b-it-abliterated)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: unsloth/gemma-3-27b-it
  - model: summykai/gemma3-27b-abliterated-dpo
  - model: mlabonne/gemma-3-27b-it-abliterated
  
merge_method: model_stock
base_model: unsloth/gemma-3-27b-it

dtype: bfloat16

tokenizer:
  source: unsloth/gemma-3-27b-it
  
chat_template: "auto"
```