From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Pretrained model selection criteria

Pretrained model selection criteria - Amazon Web Services (AWS) Tutorial

From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep

Start my 1-month free trial Buy for my team

Pretrained model selection criteria

“

- Instead of defining a number of different foundation model selection criteria, we're going to follow the experience and scenario of GlobalTech, a fictional company. They're planning to develop a multilingual customer support chatbot. The decision-making process is going to involve evaluating different pre-trained foundation models and looking for certain specific properties that will meet their business objectives. The first criteria is cost. They have budget allocated for the project and they take the time to compare different pre-trained models. They consider licensing fees and the computational costs of running these models. And what they find is that some of these models are too expensive, others fit within their budget, and they meet their needs without compromising performance. Our next criteria is modality. This is a chatbot, it's going to interact using text, and that means that GlobalTech can then focus on text-only models. They're going to explore options that can…

Contents