---
base_model:
- TheDrummer/Cydonia-22B-v1.1
- mistralai/Mistral-Small-Instruct-2409
library_name: transformers
tags:
- mergekit
- merge
license: other
---
![The Drummer turns into a Joshi Youchien](https://huggingface.co/knifeayumu/Lite-Cydonia-22B-v1.1-Test/resolve/main/Lite-Cydonia-22B-v1.1.png)

# The Drummer turns into a Joshi Youchien

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

GGUF quants : [knifeayumu/Lite-Cydonia-22B-v1.1-Test-GGUF](https://huggingface.co/knifeayumu/Lite-Cydonia-22B-v1.1-Test-GGUF)

## Inspiration

I thought [BeaverAI/Cydonia-22B-v1f-GGUF](https://huggingface.co/TheDrummer/Cydonia-22B-v1.1) and [BeaverAI/Cydonia-22B-v1e-GGUF](https://huggingface.co/BeaverAI/Cydonia-22B-v1e-GGUF) versions being a bit too evil. The sense of morality is screwed up too much and it was a bit deterministic (swipes don't give much variety) versus the base model. Then an idea propped into my mind — why not merge it back again to the base? Give it a sense of "good" back, at least a little. Maybe that should fix some of deterministic generations too.

Quick testing shows... it works? Zero-shot evil Q&A no longer works but which a bit of persuasion, it did answer. I've also tried with both weights at 0.5 but it was too moral for my liking. Hence, I uploaded this version.

Credits to [TheDrummer](https://huggingface.co/TheDrummer) and [BeaverAI](https://huggingface.co/BeaverAI) who makes such finetunes. "Lightly decensored" is a heavy understatement in this case.

## Merge Details
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [TheDrummer/Cydonia-22B-v1.1](https://huggingface.co/TheDrummer/Cydonia-22B-v1.1) as a base.

### Models Merged

The following models were included in the merge:
* [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: TheDrummer/Cydonia-22B-v1.1
    parameters:
      weight: 0.75
  - model: mistralai/Mistral-Small-Instruct-2409
    parameters:
      weight: 0.25
merge_method: task_arithmetic
base_model: TheDrummer/Cydonia-22B-v1.1
dtype: float16
```