---
base_model:
- grimjim/FranFran-Something-12B
- Nitral-AI/Nera_Noctis-12B
- Nohobby/MN-12B-Siskin-v0.2
- BarBarickoza/Dans-SakuraKaze-Picaro-12b
library_name: transformers
tags:
- mergekit
- merge

---
# 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 [Karcher Mean](https://en.wikipedia.org/wiki/Karcher_mean) merge method.

### Models Merged

The following models were included in the merge:
* [grimjim/FranFran-Something-12B](https://huggingface.co/grimjim/FranFran-Something-12B)
* [Nitral-AI/Nera_Noctis-12B](https://huggingface.co/Nitral-AI/Nera_Noctis-12B)
* [Nohobby/MN-12B-Siskin-v0.2](https://huggingface.co/Nohobby/MN-12B-Siskin-v0.2)
* [BarBarickoza/Dans-SakuraKaze-Picaro-12b](https://huggingface.co/BarBarickoza/Dans-SakuraKaze-Picaro-12b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: BarBarickoza/Dans-SakuraKaze-Picaro-12b
  - model: Nohobby/MN-12B-Siskin-v0.2
  - model: grimjim/FranFran-Something-12B
  - model: Nitral-AI/Nera_Noctis-12B
merge_method: karcher
parameters:
  t:
    - filter: self_attn
      value: [0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5]
    - filter: mlp
      value: [0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16
```