The merging approach relies on some luck, but at the same time, if I have an accurate understanding of my model's performance, I can carefully select models that excel in each aspect to develop a well-balanced model.

Thanks to maywell for sharing useful tips related to the merge method.

Model Benchmark

KO-LLM leaderboard

Follow up as Open KO-LLM LeaderBoard.

Model	Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
COKAL_merged_test-v1-13B🐻‍❄️	52.72	51.45	60.55	44.8	49.05	57.73
COKAL-DPO-13b-v2🐻‍❄️	52.69	54.95	63.02	43.98	51.67	49.82
COKAL-DPO_test-v2-13b🐻‍❄️	52.67	55.63	63.5	43.49	51.5	49.23
hyeogi/Yi-6b-dpo-v0.2	52.63	41.72	52.96	46.69	52.38	69.42
DopeorNope-maestro-v2-DPO-13b🐻‍❄️	49.42	45.14	56.69	41.37	42.26	61.63

Implementation Code

Load model

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "DopeorNope/COKAL_merged_test-v1-13B"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Prompt (Alpaca format)

python

prompt= f"아래는 문제를 설명하는 지시사항과, 구체적인 답변을 방식을 요구하는 입력이 함께 있는 문장입니다. 이 요청에 대해 적절하게 답변해주세요.\n\n### 지시사항:\n{instruction}\n\n### 입력:\n{input}\n\n### 답변:\n"

prompt_no_input = f"아래는 문제를 설명하는 지시사항입니다. 이 요청에 대해 적절하게 답변해주세요.\n\n### 지시사항:\n{instruction}\n\n### 답변:\n"

Acknowledgement

이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.