---
base_model:
- alpindale/Mistral-7B-v0.2-hf
- mistralai/Mistral-7B-Instruct-v0.2
- SanjiWatsuki/Kunoichi-DPO-v2-7B
library_name: transformers
tags:
- mergekit
- merge

---
This is an ExLlamaV2 quantized model in 4bpw of [mpasila/Kunoichi-DPO-v2-Instruct-32k-7B](https://huggingface.co/mpasila/Kunoichi-DPO-v2-Instruct-32k-7B) using the default calibration dataset.

# Original Model card:

# Kunoichi-DPO-v2-Instruct-32k-7B

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

This hopefully gives 32k context for Kunoichi-DPO-v2 model though since it also uses the instruct model it might change its behavior somewhat.

Merge script copied from this [ichigoberry/pandafish-2-7b-32k](https://huggingface.co/ichigoberry/pandafish-2-7b-32k).

## 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 [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) as a base.

### Models Merged

The following models were included in the merge:
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: alpindale/Mistral-7B-v0.2-hf
    # No parameters necessary for base model
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      density: 0.53
      weight: 0.4
  - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
    parameters:
      density: 0.53
      weight: 0.4
merge_method: dare_ties
base_model: alpindale/Mistral-7B-v0.2-hf
parameters:
  int8_mask: true
dtype: bfloat16

```