Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-rlhf-dpo-8B

Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-rlhf-dpo-8B is an 8 billion parameter Korean language model developed by Linkbricks Horizon-AI, fine-tuned from NousResearch/Meta-Llama-3.1-8B-Instruct. It utilizes SFT, RLHF, and DPO techniques with Korean-Chinese-English-Japanese cross-training data to enhance logical problem-solving in Korean. The model features a 32768-token context window and is specifically strengthened for high-level analysis of customer reviews, social media postings, and coding tasks.