---
base_model:
- huihui-ai/Mistral-Nemo-Instruct-2407-abliterated
- ParasiticRogue/Magnum-Instruct-DPO-12B
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 linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [huihui-ai/Mistral-Nemo-Instruct-2407-abliterated](https://huggingface.co/huihui-ai/Mistral-Nemo-Instruct-2407-abliterated) as a base.

### Models Merged

The following models were included in the merge:
* [ParasiticRogue/Magnum-Instruct-DPO-12B](https://huggingface.co/ParasiticRogue/Magnum-Instruct-DPO-12B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: ParasiticRogue/Magnum-Instruct-DPO-12B
    parameters:
      weight: 1.1
base_model: huihui-ai/Mistral-Nemo-Instruct-2407-abliterated
parameters:
  normalize: false
  int8_mask: true
merge_method: dare_linear
dtype: float32
out_dtype: bfloat16
tokenizer_source: base
```