Nguyen Yi Feng

On August 29th, in its latest edition of the Science and Technology Hobbies Weekly, Nguyen Fong broke down the large model process of answering questions into three mechanisms: parameters, reasoning and networking. In his view, training began with the use of parameters to establish a mathematical relationship between the words, on the basis of which the model answers produced more probabilistic elements; conclusions that the parameters did not contain directly could be obtained through logical reasoning. He summarized the parameter mechanism as "compressed-generated": the training stage encoded knowledge relationships into weights, and the generation phase relied on these weights to find the most possible next word. The more arguments are usually more detailed, but the training and reasoning costs..