DeepSeek R1 Explained - A fascinating LLM AI! скачать в хорошем качестве

DeepSeek R1 Explained - A fascinating LLM AI!

DeepSeek R1 in an open-source AI Model. It is very good at reasoning and was trained with Reinforcement Learning. It uses Mixture-of-Experts Architecture. In this video I feed it three questions including can we travel at light speed in the future? Thank you for the ever-growing support and I wish you all the best on your AI learning journey. - Sheppe 00:00 Mixture-of-Experts Approach 01:54 Reinforcement Learning 03:22 Testing Prompts 04:43 Create a Study Guide for Computer Architecture 07:14 Asking can we eventually travel the speed of light? 12:17 Creating a card game similar to Pokemon #deepseek #ai #llm