README.md

---
base_model:
- ajibawa-2023/General-Stories-Mistral-7B
- OmnicromsBrain/Eros_Scribe-7b
- NousResearch/Yarn-Mistral-7b-64k
- MrRobotoAI/Thoth-6delta
- Local-Novel-LLM-project/Ninja-v1-NSFW
- BlueNipples/Apocrypha-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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Yarn-Mistral-7b-64k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k) as a base.

### Models Merged

The following models were included in the merge:
* [ajibawa-2023/General-Stories-Mistral-7B](https://huggingface.co/ajibawa-2023/General-Stories-Mistral-7B)
* [OmnicromsBrain/Eros_Scribe-7b](https://huggingface.co/OmnicromsBrain/Eros_Scribe-7b)
* [MrRobotoAI/Thoth-6delta](https://huggingface.co/MrRobotoAI/Thoth-6delta)
* [Local-Novel-LLM-project/Ninja-v1-NSFW](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW)
* [BlueNipples/Apocrypha-7b](https://huggingface.co/BlueNipples/Apocrypha-7b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:

  - model: NousResearch/Yarn-Mistral-7b-64k
    parameters:
      weight: 0.1
      density: 0.8

  - model: MrRobotoAI/Thoth-6delta
    parameters:
      weight: 0.6
      density: 0.8
  - model: Local-Novel-LLM-project/Ninja-v1-NSFW
    parameters:
      weight: 0.05
      density: 0.8
 
  - model: OmnicromsBrain/Eros_Scribe-7b
    parameters:
      weight: 0.15
      density: 0.8
  - model: ajibawa-2023/General-Stories-Mistral-7B
    parameters:
      weight: 0.05
      density: 0.8
  - model: BlueNipples/Apocrypha-7b
    parameters:
      weight: 0.05
      density: 0.8
      
merge_method: ties
base_model: NousResearch/Yarn-Mistral-7b-64k
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```