---
base_model:
- BAAI/Infinity-Instruct-7M-Gen-mistral-7B
- mikewang/PVD-160k-Mistral-7b
- Anarchist/mistral_7b_lora_smol_pippa
- kittn/mistral-7B-v0.1-hf
- Epiculous/Mika-7B
- Intel/neural-chat-7b-v3
- openchat/openchat-3.5-0106
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- jeiku/Synthetic_Soul_1k_Mistral_128
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 [kittn/mistral-7B-v0.1-hf](https://huggingface.co/kittn/mistral-7B-v0.1-hf) as a base.

### Models Merged

The following models were included in the merge:
* [BAAI/Infinity-Instruct-7M-Gen-mistral-7B](https://huggingface.co/BAAI/Infinity-Instruct-7M-Gen-mistral-7B)
* [mikewang/PVD-160k-Mistral-7b](https://huggingface.co/mikewang/PVD-160k-Mistral-7b) + [Anarchist/mistral_7b_lora_smol_pippa](https://huggingface.co/Anarchist/mistral_7b_lora_smol_pippa)
* [Epiculous/Mika-7B](https://huggingface.co/Epiculous/Mika-7B)
* [Intel/neural-chat-7b-v3](https://huggingface.co/Intel/neural-chat-7b-v3)
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B) + [jeiku/Synthetic_Soul_1k_Mistral_128](https://huggingface.co/jeiku/Synthetic_Soul_1k_Mistral_128)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Intel/neural-chat-7b-v3
    parameters:
      weight: 1
  - model: openchat/openchat-3.5-0106
    parameters:
      weight: 1
  - model: BAAI/Infinity-Instruct-7M-Gen-mistral-7B
    parameters:
      weight: 1
  - model: mikewang/PVD-160k-Mistral-7b+Anarchist/mistral_7b_lora_smol_pippa
    parameters:
      weight: 1
  - model: SanjiWatsuki/Kunoichi-DPO-v2-7B+jeiku/Synthetic_Soul_1k_Mistral_128
    parameters:
      weight: 1
  - model: Epiculous/Mika-7B
    parameters:
      weight: 1

merge_method: ties
base_model: kittn/mistral-7B-v0.1-hf
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16
```