---
base_model:
- jeiku/NarrativeNexus_7B
- mlabonne/AlphaMonarch-7B
- CultriX/NeuralTrix-bf16
- jeiku/Cookie_7B
- jeiku/Luna_7B
library_name: transformers
tags:
- mergekit
- merge

---
# Fine

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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mlabonne/AlphaMonarch-7B](https://huggingface.co./mlabonne/AlphaMonarch-7B) as a base.

### Models Merged

The following models were included in the merge:
* [jeiku/NarrativeNexus_7B](https://huggingface.co./jeiku/NarrativeNexus_7B)
* [CultriX/NeuralTrix-bf16](https://huggingface.co./CultriX/NeuralTrix-bf16)
* [jeiku/Cookie_7B](https://huggingface.co./jeiku/Cookie_7B)
* [jeiku/Luna_7B](https://huggingface.co./jeiku/Luna_7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: dare_ties
base_model: mlabonne/AlphaMonarch-7B
parameters:
  normalize: true
models:
  - model: jeiku/Luna_7B
    parameters:
      weight: 0.75
  - model: jeiku/Cookie_7B
    parameters:
      weight: 1
  - model: jeiku/NarrativeNexus_7B
    parameters:
      weight: 0.5
  - model: CultriX/NeuralTrix-bf16
    parameters:
      weight: 0.75
  - model: mlabonne/AlphaMonarch-7B
    parameters:
      weight: 1           
dtype: float16

```