Small Language Models

Author(s): Lalit Kumar

Originally published on Towards AI.

This member-only story is on us. Upgrade to access all of Medium.

If you are not a Medium member, you can read this article here.

Large language models have become very popular recently due to the amazing capabilities shown by these models. Their applicability to automate coding, text generation has shown vast potential and applicability across various domains. But these models currently have many limitations due to their requirements of memory, processing power, storage and energy. This is why LLMs mostly are deployed on cloud platforms like AWS, Google cloud or Azure.

These limitations have led researchers to look for solutions which enables deployment of language models of devices with lesser specs like personal computers or mobile devices. One of the popular areas of research in this field is SLM i.e. .

A Small Language Model is a language model with number of parameters limited to millions to few billions. Basically, these are the models which can run on an edge devices like mobile phones, industrial equipments or in car controls. The focus of these models is to enable effective Edge AI [Read more about Edge AI in my other article here].

Think about the less powerful phones, the kind that struggle with… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI