--- language: - ko - en - jp - cn license: apache-2.0 library_name: transformers base_model: google/gemma-2-27b-it datasets: - Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset - Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset - Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface - Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface - Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface - Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface - Saxo/OpenOrca_cleaned_kor_linkbricks_single_dataset_with_prompt_text_huggingface - Saxo/ko_government_qa_total_linkbricks_single_dataset_with_prompt_text_huggingface_sampled - Saxo/ko-news-corpus-1 - Saxo/ko-news-corpus-2 - Saxo/ko-news-corpus-3 - Saxo/ko-news-corpus-4 - Saxo/ko-news-corpus-5 - Saxo/ko-news-corpus-6 - Saxo/ko-news-corpus-7 - Saxo/ko-news-corpus-8 - Saxo/ko-news-corpus-9 - maywell/ko_Ultrafeedback_binarized - youjunhyeok/ko-orca-pair-and-ultrafeedback-dpo - lilacai/glaive-function-calling-v2-sharegpt - kuotient/gsm8k-ko pipeline_tag: text-generation model-index: - name: Linkbricks-Horizon-AI-Korean-Superb-27B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 77.68 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 50.61 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 26.96 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 14.65 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 19.53 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 40.52 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B name: Open LLM Leaderboard --- # Model Card for Model ID
AI 와 빅데이터 분석 전문 기업인 Linkbricks의 데이터사이언티스트인 지윤성(Saxo) 박사가
gemma-2-27b-it 베이스모델을 사용해서 H100-80G 8개를 통해 약 38%정도의 파라미터를 한국어 CPT(Continued-Pretraining)->SFT->DPO 한 한글 언어 모델
9천만건의 한글 뉴스 코퍼스를 기준으로 다양한 테스크별 한국어-중국어-영어-일본어 교차 학습 데이터와 수학 및 논리판단 데이터를 통하여 한중일영 언어 교차 증강 처리와 복잡한 논리 문제 역시 대응 가능하도록 훈련한 모델이다.
-토크나이저는 단어 확장 없이 베이스 모델 그대로 사용
-고객 리뷰나 소셜 포스팅 고차원 분석 및 코딩과 작문, 수학, 논리판단 등이 강화된 모델
-128k-Context Window
-Deepspeed Stage=3, rslora 및 BAdam Layer Mode 사용
"transformers_version": "4.46.1"

Finetuned by Mr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics
about 38% of total parameters Korean CPT(Continued-Pretraining)->SFT->DPO training model based on gemma-2-27b-it through 8 H100-80Gs as a Korean language model
It is a model that has been trained to handle Korean-Chinese-English-Japanese cross-training data and 90M korean news corpus and logic judgment data for various tasks to enable cross-fertilization processing and complex Korean logic & math problems.
-Tokenizer uses the base model without word expansion
-Models enhanced with high-dimensional analysis of customer reviews and social posts, as well as coding, writing, math and decision making
-128k-Context Window
-Deepspeed Stage=3, use rslora and BAdam Layer Mode


www.linkbricks.com, www.linkbricks.vc # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Saxo__Linkbricks-Horizon-AI-Korean-Superb-27B) | Metric |Value| |-------------------|----:| |Avg. |38.32| |IFEval (0-Shot) |77.68| |BBH (3-Shot) |50.61| |MATH Lvl 5 (4-Shot)|26.96| |GPQA (0-shot) |14.65| |MuSR (0-shot) |19.53| |MMLU-PRO (5-shot) |40.52|