👀 On-Device LLM Research

We are the SK Devocean On-Device LLM (Large Language Model) Team.
Our goal is to enable LLMs to run efficiently on mobile and edge devices through model compression, optimization, pruning, and quantization.

🚀 Focus Areas

• Model Compression & Optimization: quantization, pruning, knowledge distillation
• On-Device AI Services: spam filtering, summarization, translation, and more real-world applications
• Open Research Sharing: publishing experimental results and models as open source