Natural Language Processing (NLP) has rapidly evolved in the last few years, with transformers emerging as a game-changing innovation. Yet, there are still notable challenges when using NLP tools to develop applications for tasks like semantic search, question answering, or document embedding. One key issue has been the need for models that not only perform well but also work efficiently on a range of devices, especially those with limited computational resources, such as CPUs. Models tend to require substantial processing power to yield high accuracy, and this trade-off often leaves developers choosing between performance and practicality. Additionally, deploying large models
