Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B

Model Overview

Developed by Yunsung Ji (Saxo), a data scientist at Linkbricks Horizon-AI, this model is an 8 billion parameter Korean language model. It is a fine-tuned version of the Meta-Llama-3.1-8B-Instruct base model, utilizing SFT (Supervised Fine-Tuning) and DPO (Direct Preference Optimization) techniques.

Key Capabilities

• Multilingual Processing: Enhanced with Korean-Chinese-English-Japanese cross-training data, allowing for improved understanding and generation across these languages.
• Logical Reasoning: Specifically trained with logical data to address and solve complex Korean logical problems effectively.
• Specialized Analysis: Strengthened for high-level analysis of customer reviews and social media postings.
• Coding Proficiency: Demonstrates enhanced capabilities in coding tasks.
• Extended Context Window: Supports a 32,768-token context window, enabling processing of longer inputs.
• Tool Calling: Includes support for tool calling functionalities.

Intended Use Cases

This model is particularly well-suited for applications requiring:

• Advanced Korean language understanding and generation.
• Solving complex logical problems in Korean.
• Detailed sentiment and content analysis from customer feedback and social media.
• Code generation and related programming tasks.
• Multilingual applications involving Korean, Chinese, English, and Japanese.