(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다
The license is cc-by-nc-sa-4.0.

🐳Korean-OpenOrca-13B🐳

Model Details

Model Developers Kyujin Han (kyujinpy)

Input Models input text only.

Output Models generate text only.

Model Architecture
Korean-OpenOrca-13B is an auto-regressive language model based on the LLaMA2 transformer architecture.

Repo Link
Github Korean-OpenOrca: 🐳Korean-OpenOrca🐳

Base Model hyunseoki/ko-en-llama2-13b

Training Dataset
I use OpenOrca-KO.
Using DeepL, translate about OpenOrca.

I use A100 GPU 40GB and COLAB, when trianing.

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
Korean-OpenOrca-13B(ours🐳)	47.85	43.09	54.13	40.24	45.22	56.57
KoT-Platypus2-13B	49.55	43.69	53.05	42.29	43.34	65.38
KO-Platypus2-13B	47.90	44.20	54.31	42.47	44.41	54.11
hyunseoki/ko-en-llama2-13b	46.68	42.15	54.23	38.90	40.74	57.39
MarkrAI/kyujin-CoTy-platypus-ko-12.8b	46.44	34.98	49.11	25.68	37.59	84.86

Compare with Top 4 SOTA models. (update: 10/09)

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

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

---