Model Card for Model ID
AI μ λΉ
λ°μ΄ν° λΆμ μ λ¬Έ κΈ°μ
μΈ Linkbricksμ λ°μ΄ν°μ¬μ΄μΈν°μ€νΈμΈ μ§μ€μ±(Saxo) μ΄μ¬κ° Meta-Llama-3.1-8B-Instruct λ² μ΄μ€λͺ¨λΈμ KT-CLOUDμμ H100-80G 4κ°λ₯Ό ν΅ν΄ SFT->DPO νμΈ νλμ ν
νκΈ μΈμ΄ λͺ¨λΈλ‘ νκ΅μ΄-μ€κ΅μ΄-μμ΄-μΌλ³Έμ΄ κ΅μ°¨ νμ΅ λ°μ΄ν°μ λ‘μ§μ»¬ λ°μ΄ν°λ₯Ό ν΅νμ¬ νμ€μΌμ μΈμ΄ κ΅μ°¨ μ¦κ° μ²λ¦¬μ 볡μ‘ν νκΈ λ
Όλ¦¬ λ¬Έμ μμ λμ κ°λ₯νλλ‘ νλ ¨ν λͺ¨λΈμ΄λ©° ν ν¬λμ΄μ λ λ¨μ΄ νμ₯ μμ΄ λ² μ΄μ€ λͺ¨λΈ κ·Έλλ‘ μ¬μ©.
νΉν κ³ κ° λ¦¬λ·°λ μμ
ν¬μ€ν
κ³ μ°¨μ λΆμ λ° μ½λ©λ±μ΄ κ°νλ λͺ¨λΈ, 128k-Context Window, Tool Calling μ§μ
Deepspeed Stage=3, rsloraλ₯Ό μ¬μ©
ollama run benedict/linkbricks-llama3.1-korean:8b
Dr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics, fine-tuned the Meta-Llama-3.1-8B-Instruct 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.
- Downloads last month
- 918
Model tree for Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B
Base model
meta-llama/Llama-3.1-8B