LLM

LG AI Research Institute (President Bae Kyung-hoon) announced on the tenth that it had released three models based on 'EXAONE 3.5' as open source. That is an update conducted 4 months after the discharge of...

Telefix (CEO Cho Seong-ik), a satellite solution specialist, announced on the third that it has officially launched the world's first satellite-specific artificial intelligence (AI)-based chatbot service, 'SatCHAT'. That is the official launch about 5...

Squeeze Beats (CEO Kim Hyeong-jun), a specialist in artificial intelligence (AI) lightweighting and optimization, announced on the third that it has launched 'Matches on Chips', a customized solution for serving large language models (LLM). Matches...

MOREH (CEO Jo Kang-won), a specialist in artificial intelligence (AI) infrastructure solutions, has opened its self-developed Korean foundation large language model (LLM) 'Llama-3-Motif-102B' to Hugging Face. It was announced on the third that it...

As AI engineers, crafting clean, efficient, and maintainable code is critical, especially when constructing complex systems.Design patterns are reusable solutions to common problems in software design. For AI and enormous language model (LLM) engineers,...

When your enterprise doesn’t use public models like OpenAIStarting with LlamaIndex is a fantastic alternative when constructing an RAG pipeline. Normally, you wish an OpenAI API key to follow the numerous tutorials available.Nevertheless, you...

Going beyond the present Search Augmented Generation (RAG), which conducts searches based on a single knowledge source, predictions have emerged that so-called 'RAG agents', which extract information from multiple knowledge sources using various tools,...

As developers and researchers push the boundaries of LLM performance, questions on efficiency loom large. Until recently, the main focus has been on increasing the dimensions of models and the amount of coaching data,...