README.md

---
base_model:
- Undi95/Xwin-MLewd-13B-V0.2
- Undi95/PsyMedRP-v1-13B
library_name: transformers
tags:
- mergekit
- merge

---


![Warning: Cute Harlequin Gal inside!](https://huggingface.co/Elfrino/PsyMedLewdPass/resolve/main/FriendlyBotGal_V2.png)


***notes:***

Creative, articulate and has a wacky sense of humour with the right settings:

RECOMMENDED SETTINGS:

(based on KoboldCPP):

Preset: Mayday

Temperature - 1.3

Max Ctx. Tokens - 4096

Top p Sampling - 0.99

Repetition Penalty - 1.1

Amount to Gen. - 280

***New findings:***


around 47 layers offloaded to GPU

Smartcontext enabled

Custom RoPe Config enabled (but left as default)

Prompt template: Alpaca



# 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 passthrough merge method.

### Models Merged

The following models were included in the merge:
* [Undi95/Xwin-MLewd-13B-V0.2](https://huggingface.co/Undi95/Xwin-MLewd-13B-V0.2)
* [Undi95/PsyMedRP-v1-13B](https://huggingface.co/Undi95/PsyMedRP-v1-13B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: Undi95/PsyMedRP-v1-13B
        layer_range: [0, 16]
  - sources:
      - model: Undi95/Xwin-MLewd-13B-V0.2
        layer_range: [8, 24]
  - sources:
      - model: Undi95/PsyMedRP-v1-13B
        layer_range: [17, 32]
  - sources:
      - model: Undi95/Xwin-MLewd-13B-V0.2
        layer_range: [25, 40]
merge_method: passthrough
dtype: float16
```