Key Points:
SLMs with 1-8B parameters can perform as well or better than LLMs. SLMs are task-agnostic or task-specific. SLMs balance performance, efficiency, scalability, and cost. SLMs are effective in resource-constrained environments. SLMs can be trained on consumer-grade GPUs. SLMs include models like #Llama2, #Mistral, #Phi, and #Gemini.
arXiv.orgSmall Language Models (SLMs) Can Still Pack a Punch: A surveyAs foundation AI models continue to increase in size, an important question arises - is massive scale the only path forward? This survey of about 160 papers presents a family of Small Language Models (SLMs) in the 1 to 8 billion parameter range that demonstrate smaller models can perform as well, or even outperform large models. We explore task agnostic, general purpose SLMs, task-specific SLMs and techniques to create SLMs that can guide the community to build models while balancing performance, efficiency, scalability and cost. Furthermore we define and characterize SLMs' effective sizes, representing increased capability with respect to LLMs.
Enter … 
Listen now: 