Distilling Step-by-Step : Paper Review

Author(s): Marcello Politi

Originally published on Towards AI.

Photo by Dan Cristian Pădureț on Unsplash

This blog post was written by Marcello Politi and Vijayasri Iyer.

Nowadays, large language models are quite prominent. Recent trends in AI Research have shown that larger LMs have zero-shot generalization capabilities and emergent/common sense reasoning abilities. Currently, one of the biggest language models is the 540B PaLM model. Companies want to use Large Language Models (LLMs) and customize them to their use cases. The problem is that deploying and serving these models independently is not always feasible in terms of costs and specialized hardware.

In the recent paper by Google AI, “Distilling Step by Step”,… 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