Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base

Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base is an 8 billion parameter language model developed by Dr. Yunsung Ji (Saxo) at Linkbricks, fine-tuned from Meta-Llama-3-8B. This model underwent Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) training specifically for Korean language tasks. It leverages the original Llama 3 tokenizer without Korean vocabulary expansion, making it suitable for applications requiring a Korean-focused LLM based on a robust Llama 3 foundation.