Overview

StableLM - An Open-Source Language Model Suite by StabilityAI

StableLM is a new open-source language model suite by StabilityAI, launched in April 2021. It is an alpha version available in 3 billion and 7 billion parameters, with 15 billion to 65 billion parameter models to follow. StableLM is trained on a new experimental dataset built on The Pile, three times larger with 1.5 trillion tokens of content. The richness of this dataset gives StableLM surprisingly high performance in conversational and coding tasks, despite its small size of 3 to 7 billion parameters.

Use cases:

StableLM models will power a range of downstream applications such as chatbots, virtual assistants, and more. The StableLM suite of models demonstrates how small and efficient models can deliver high performance with appropriate training.


Comments