---
base_model:
- sh2orc/Llama-3.1-Korean-8B-Instruct
- NousResearch/Meta-Llama-3.1-8B-Instruct
- allenai/Llama-3.1-Tulu-3-8B-DPO
library_name: transformers
tags:
- mergekit
- merge

---
# Llama-3.1-Sisaai-Ko-Tulu-DPO-Merge-8B

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 [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [sh2orc/Llama-3.1-Korean-8B-Instruct](https://huggingface.co/sh2orc/Llama-3.1-Korean-8B-Instruct)
* [allenai/Llama-3.1-Tulu-3-8B-DPO](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-DPO)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
merge_method: dare_ties

models:
  - model: "allenai/Llama-3.1-Tulu-3-8B-DPO"
    parameters:
      density: 0.55
      weight: 0.30

  - model: "sh2orc/Llama-3.1-Korean-8B-Instruct"
    parameters:
      density: 0.75
      weight: 0.70

tokenizer_source: "sh2orc/Llama-3.1-Korean-8B-Instruct"
dtype: float16
int8_mask: false


```