---
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
- DarkArtsForge/MN-Raven-12B-v1
- Lambent/Arsenic-Shahrazad-12B-v4.4
- Retreatcost/Evertide-RX-12B
- WokeAI/Tankie-DPE-12B-SFT-v2
datasets:
- OccultAI/illuminati_imatrix_v1
language:
- en
library_name: transformers
license: apache-2.0
tags:
- merge
- mergekit
- mistral
- nemo
- della
- creative
- roleplay
- creative-writing
- creative-roleplay
widget:
- text: "Vesper-Zenith-12B"
output:
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/8sWlwh-FjfgmXXys60Av7.png
---
CREATIVITYUNBOUND
ROLEPLAYIMMERSIVE
LOGICENHANCED
🌌 About The Model
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
It's recommended to use the `ChatML` template with this model, although it also works with `Mistral Tekken`.
There are some refusals but it's very creative and sadistic when prompted, and it can be ablated or jailbroken if needed.
---
## Merge Details
### Merge Method
This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.
### Models Merged
The following models were included in the merge:
- [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
- [DarkArtsForge/MN-Raven-12B-v1](https://huggingface.co/DarkArtsForge/MN-Raven-12B-v1)
- [Lambent/Arsenic-Shahrazad-12B-v4.4](https://huggingface.co/Lambent/Arsenic-Shahrazad-12B-v4.4)
- [Retreatcost/Evertide-RX-12B](https://huggingface.co/Retreatcost/Evertide-RX-12B)
- [WokeAI/Tankie-DPE-12B-SFT-v2](https://huggingface.co/WokeAI/Tankie-DPE-12B-SFT-v2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
architecture: MistralForCausalLM
base_model: B:\12B\mistralai--Mistral-Nemo-Instruct-2407
models:
- model: B:\12B\MN-Raven-12B-v1
parameters:
weight: 0.25
density: 0.9
epsilon: 0.09
- model: B:\12B\Lambent--Arsenic-Shahrazad-12B-v4.4
parameters:
weight: 0.25
density: 0.9
epsilon: 0.09
- model: B:\12B\Retreatcost--Evertide-RX-12B
parameters:
weight: 0.25
density: 0.9
epsilon: 0.09
- model: B:\12B\WokeAI--Tankie-DPE-12B-SFT-v2
parameters:
weight: 0.25
density: 0.9
epsilon: 0.09
merge_method: della
parameters:
lambda: 1.0
normalize: false
int8_mask: false
rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: union
chat_template: auto
```