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

---
## **✨ Subscribe My YouTube Channel ✨**  
### 👉 [**시사AI**](https://www.youtube.com/@JayLee-gv8tv) 👈  
### 👉 [**Shorts Tulu3+Korean Merge**](https://www.youtube.com/shorts/s_M8WEFoZl8) 👈  

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

By merging it with a Korean language model, the following benefits arise:

Korean with logical reasoning, mathematical problem-solving, and reliability (TruthfulQA)

Maybe not repeating response? 

### 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)