metadata

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 👈

👉 Shorts Tulu3+Korean Merge 👈

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 TIES merge method using 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
allenai/Llama-3.1-Tulu-3-8B-DPO