Model Card for Model ID


Open Ko LLM Leaderboard Season 2 πŸ† Rank-4 2024/11/01~


AI μ „λ¬Έ 기업인 Linkbricks Horizon-AI 의 λ°μ΄ν„°μ‚¬μ΄μ–Έν‹°μŠ€νŠΈμΈ μ§€μœ€μ„±(Saxo) λŒ€ν‘œκ°€ Mistral-Nemo-Instruct-2407 베이슀λͺ¨λΈμ„ KT-CLOUDμƒμ˜ H100-80G 4개λ₯Ό 톡해 SFT->DPO 파인 νŠœλ‹μ„ ν•œ ν•œκΈ€ μ–Έμ–΄ λͺ¨λΈλ‘œ ν•œκ΅­μ–΄-쀑ꡭ어-μ˜μ–΄-일본어 ꡐ차 ν•™μŠ΅ 데이터와 λ‘œμ§€μ»¬ 데이터λ₯Ό ν†΅ν•˜μ—¬ ν•œμ€‘μΌμ˜ μ–Έμ–΄ ꡐ차 증강 μ²˜λ¦¬μ™€ λ³΅μž‘ν•œ ν•œκΈ€ 논리 문제 μ—­μ‹œ λŒ€μ‘ κ°€λŠ₯ν•˜λ„λ‘ ν›ˆλ ¨ν•œ λͺ¨λΈμ΄λ©° ν† ν¬λ‚˜μ΄μ €λŠ” 단어 ν™•μž₯ 없이 베이슀 λͺ¨λΈ κ·ΈλŒ€λ‘œ μ‚¬μš©. 특히 고객 λ¦¬λ·°λ‚˜ μ†Œμ…œ ν¬μŠ€νŒ… 고차원 뢄석 및 코딩등이 κ°•ν™”λœ λͺ¨λΈ, Context Window Size=128K Deepspeed Stage=3, rslora λ₯Ό μ‚¬μš©
ollama run benedict/linkbricks-mistral-nemo-korean:12b

CEO Yunsung Ji (Saxo), a data scientist at Linkbricks Horizon-AI, a company specializing in AI and big data analytics, fine-tuned the Mistral-Nemo-Instruct-2407 base model with SFT->DPO using four H100-80Gs on KT-CLOUD. It is a Korean language model trained to handle complex Korean logic problems through Korean-Chinese-English-Japanese cross-training data and logical data, and Tokenizer uses the base model without word expansion.

www.horizonai.ai, www.linkbricks.com, www.linkbricks.vc

Downloads last month
2,230
Safetensors
Model size
12.2B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Saxo/Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B

Quantized
(117)
this model
Quantizations
2 models

Datasets used to train Saxo/Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B

Space using Saxo/Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B 1