---
base_model:
- Undi95/BigL-7B
- Undi95/LewdMistral-7B-0.2
- Undi95/Mistral-ClaudeLimaRP-v3-7B
- Undi95/MistRP-Dolphin-7B
- Undi95/Toppy-M-7B
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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Undi95/Toppy-M-7B](https://huggingface.co./Undi95/Toppy-M-7B) as a base.

### Models Merged

The following models were included in the merge:
* [Undi95/BigL-7B](https://huggingface.co./Undi95/BigL-7B)
* [Undi95/LewdMistral-7B-0.2](https://huggingface.co./Undi95/LewdMistral-7B-0.2)
* [Undi95/Mistral-ClaudeLimaRP-v3-7B](https://huggingface.co./Undi95/Mistral-ClaudeLimaRP-v3-7B)
* [Undi95/MistRP-Dolphin-7B](https://huggingface.co./Undi95/MistRP-Dolphin-7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:

  - model: Undi95/BigL-7B
    parameters:
      weight: 0.2
      density: 0.9
  - model: Undi95/LewdMistral-7B-0.2
    parameters:
      weight: 0.2
      density: 0.9
  - model: Undi95/Mistral-ClaudeLimaRP-v3-7B
    parameters:
      weight: 0.2
      density: 0.9
  - model: Undi95/MistRP-Dolphin-7B
    parameters:
      weight: 0.2
      density: 0.9
  - model: Undi95/Toppy-M-7B
    parameters:
      weight: 0.2
      density: 0.9

merge_method: dare_ties
base_model: Undi95/Toppy-M-7B
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```