Gorilla — Enhancing Large Language Models’ Ability to Use API Calls

Author(s): Marcello Politi

Originally published on Towards AI.

A Finetuned LLaMA-based Model to Improve LLMs’ API Call Accuracy and Adaptability

Photo by Valentin Jorel on Unsplash

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

Large Language Models today are limited in the amount of information they can capture in their weights, and furthermore, they have a limited context. Therefore, people started to come out with methods to increase the capabilities of these LLMs by allowing them to go to external resources through API calls. For example, an LLM might not have any information about an event that happened recently, but with a simple API call to Wikipedia, it could learn about that event and answer questions.

(Image By Author)

Many… 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