---
base_model:
- Delta-Vector/Austral-24B-Winton
- Delta-Vector/MS3.2-Austral-24B-KTO
- ReadyArt/The-Omega-Directive-M-24B-v1.1
- PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
library_name: transformers
tags:
- mergekit
- merge

---
# Merge overview

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). There are no higher quants available for this model, only one due to hardware limitations. 

## Merge Details
### Merge Method

This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [PocketDoc/Dans-PersonalityEngine-V1.3.0-24b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b) as a base.
The intention of this merge is to essensially make a model that is capable of roleplaying in NSFW,SFW settings all in one, with smarts involved. Moreover overlap multiple unique writing styles.





### Models Merged

The following models were included in the merge:
* [Delta-Vector/Austral-24B-Winton](https://huggingface.co/Delta-Vector/Austral-24B-Winton)
* [ReadyArt/The-Omega-Directive-M-24B-v1.1](ReadyArt/The-Omega-Directive-M-24B-v1.1)
* [PocketDoc/Dans-PersonalityEngine-V1.3.0-24b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b)
* [Delta-Vector/MS3.2-Austral-24B-KTO](https://huggingface.co/Delta-Vector/MS3.2-Austral-Winton)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Delta-Vector/MS3.2-Austral-24B-KTO
    parameters:
      weight: 0.3
      density: 0.3
  - model: Delta-Vector/Austral-24B-Winton
    parameters:
      weight: 0.3
      density: 0.5
  - model: ReadyArt/The-Omega-Directive-M-24B-v1.1
    parameters:
      weight: 0.2
      density: 0.3
merge_method: ties
base_model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
dtype: bfloat16
outtype: bfloat16
```

### Usage guide

The prompting format is refered to as Dan's chat for this model.

```yaml
<|system|>system prompt<|endoftext|><|user|>Hi there!<|endoftext|><|assistant|>Hey, how can I help?<|endoftext|>
```


I would advise starting with adaptive.p at the settings:
target: 0,55
decay: 0.9
min_p: 0.04 

You are free to experiment to set samplers to your liking, this model is under testing phase and users are free to experiment with samplers. The only main requirement is Prompt guide.