Category: NLP

  • Attention to LLM Architectures: An Intelligent ML Engineering Guide

    Attention to LLM Architectures: An Intelligent ML Engineering Guide

    The article presents an informed view on different architectures used in modern language models (LLMs), including Encoder-Decoder, Encoder-Only, and Decoder-Only models. It defines their functions and specific uses. While the less complex Decoder-Only models like GPT have achieved excellent results, the article suggests that the choice of model should depend on the end application and…

  • Not-So-Large Language Models: Good Data Overthrows the Goliath

    Not-So-Large Language Models: Good Data Overthrows the Goliath

    In this article, we will see how Language Models (LM) can focus on better data and training strategies rather than just brute size to achieve LLM-like results (sometimes even better) and how people are already doing it successfully and democratically.