MoonMega-12B / README.md
Vortex5's picture
Update README.md
610d375 verified
---
base_model:
- anthracite-org/magnum-v4-12b
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- elinas/Chronos-Gold-12B-1.0
- Epiculous/Violet_Twilight-v0.2
- LatitudeGames/Muse-12B
- yamatazen/NeonMaid-12B-v2
- Vortex5/Moonviolet-12B
- natong19/Mistral-Nemo-Instruct-2407-abliterated
library_name: transformers
tags:
- mergekit
- merge
- roleplay
---
# MoonMega-12B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6669a3a617b838fda45637b8/ueDOFPsGlDrD5_IrhTQ7N.png)
## Merge Details
### Merge Method
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [natong19/Mistral-Nemo-Instruct-2407-abliterated](https://huggingface.co/natong19/Mistral-Nemo-Instruct-2407-abliterated) as a base.
### Models Merged
The following models were included in the merge:
* [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b)
* [HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407](https://huggingface.co/HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407)
* [elinas/Chronos-Gold-12B-1.0](https://huggingface.co/elinas/Chronos-Gold-12B-1.0)
* [Epiculous/Violet_Twilight-v0.2](https://huggingface.co/Epiculous/Violet_Twilight-v0.2)
* [LatitudeGames/Muse-12B](https://huggingface.co/LatitudeGames/Muse-12B)
* [yamatazen/NeonMaid-12B-v2](https://huggingface.co/yamatazen/NeonMaid-12B-v2)
* [Vortex5/Moonviolet-12B](https://huggingface.co/Vortex5/Moonviolet-12B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
models:
- model: Vortex5/Moonviolet-12B
- model: LatitudeGames/Muse-12B
- model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- model: anthracite-org/magnum-v4-12b
- model: elinas/Chronos-Gold-12B-1.0
- model: yamatazen/NeonMaid-12B-v2
- model: Epiculous/Violet_Twilight-v0.2
merge_method: model_stock
dtype: bfloat16
parameters:
normalize: true
tokenizer:
source: union
```