---
base_model:
- Aleteian/Saiga-Unleashed
- nbeerbower/Lyra4-Gutenberg2-12B
- Aleteian/NeverendingStory
- LatitudeGames/Wayfarer-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 [Model Breadcrumbs with TIES](https://arxiv.org/abs/2312.06795) merge method using [Aleteian/Saiga-Unleashed](https://huggingface.co/Aleteian/Saiga-Unleashed) as a base.

### Models Merged

The following models were included in the merge:
* [nbeerbower/Lyra4-Gutenberg2-12B](https://huggingface.co/nbeerbower/Lyra4-Gutenberg2-12B)
* [Aleteian/NeverendingStory](https://huggingface.co/Aleteian/NeverendingStory)
* [LatitudeGames/Wayfarer-12B](https://huggingface.co/LatitudeGames/Wayfarer-12B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models: 
  - model: Aleteian/Saiga-Unleashed
    parameters:
      weight: 0.4

  - model: Aleteian/NeverendingStory
    parameters:
      density: 0.95
      weight: 0.4
      gamma: 0.01
      
  - model: LatitudeGames/Wayfarer-12B
    parameters:
      density: 0.9
      weight: 0.1
      gamma: 0.01      
      
  - model: nbeerbower/Lyra4-Gutenberg2-12B
    parameters:
      density: 0.9
      weight: 0.1
      gamma: 0.01      

merge_method: breadcrumbs_ties
base_model: Aleteian/Saiga-Unleashed
dtype: bfloat16

tokenizer_source: "union"
chat_template: "auto"

```