Why in News? A few days after Meta unveiled its Llama 3 Large Language Model (LLM), Microsoft unveiled the latest version of its ‘lightweight’ AI model- Phi-3-Mini.

What are Language Models? Language models are the backbone of AI applications like ChatGPT, Claude, Gemini, etc. These models are trained on existing data to solve common language problems such as text classification, answering questions, text generation, document summarisation, etc.

What is Phi-3-Mini? Microsoft has described the Phi-3 as a family of open AI models that are the most capable and cost-effective small language models (SLMs) available. Phi-3-Mini is believed to be first among the three small models that Microsoft is planning to release. It has reportedly outperformed models of the same size in areas like language, reasoning, coding, and maths.

What’s New in Microsoft’s Phi-3-Mini? Phi-3-mini (a 3.8B language model) is the first model in its class to support a context window of up to 128K tokens, with little impact on quality. The amount of conversation that an AI can read and write at any given time is called the context window, and is measured in tokens.

How is Phi-3-Mini Different from LLMs? Phi-3-mini is an SLM. Simply, SLMs are more streamlined versions of LLMs. The ‘Large’ in LLMs has two meanings - the enormous size of training data and the parameter count (memories and knowledge that a machine has learned during its model training). When compared to LLMs, smaller AI models are cost-effective to develop and operate and they perform better on smaller devices like laptops and smartphones. SLMs are great for resource-constrained environments including on-device and offline inference scenarios.