README.md

---
base_model:
- NeverSleep/Lumimaid-v0.2-12B
- intervitens/mini-magnum-12b-v1.1
- nbeerbower/mistral-nemo-gutenberg-12B-v4
- natong19/Mistral-Nemo-Instruct-2407-abliterated
- Lambent/arsenic-nemo-unleashed-12B
library_name: transformers
tags:
- mergekit
- merge

---
![image/png](https://huggingface.co/yamatazen/Amelia-SCE-12B/resolve/main/Amelia-SCE-12B.png?download=true)
This model was created without merging ChatML models.
# 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 [SCE](https://arxiv.org/abs/2408.07990) 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:
* [NeverSleep/Lumimaid-v0.2-12B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B)
* [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1)
* [nbeerbower/mistral-nemo-gutenberg-12B-v4](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v4)
* [Lambent/arsenic-nemo-unleashed-12B](https://huggingface.co/Lambent/arsenic-nemo-unleashed-12B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
models:
  - model: Lambent/arsenic-nemo-unleashed-12B
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
  - model: NeverSleep/Lumimaid-v0.2-12B
  - model: intervitens/mini-magnum-12b-v1.1
merge_method: sce
dtype: bfloat16
parameters:
  normalize: true
  select_topk: 0.5
```