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.
Question breakdown, part 2 - Amazon Web Services (AWS) Tutorial
From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep
Question breakdown, part 2
- In this practice question, we are going to look at a scenario that involves customizing an AI model in the context of customer support. So here's the question. A tech startup is looking to deploy an NLP, natural language processing model, tailored for customer support. They want a solution that minimizes costs while allowing for rapid implementation and flexibility in adjusting the model's responses based on specific queries. Which customization approach should they choose? And we have four options here. Pre-training, fine tuning, in-context learning, and RAG, which stands for retrieval-augmented generation. Let's walk through these and see if we can identify the differences between them so that we can determine whether or not they meet the requirements. Pre-training. Pre-training is when you build the model in the first place. You can get a highly specialized model out of this, but it's resource-intensive, it's time-consuming, and that's not necessarily what we're looking for here.…
Contents
-
-
-
-
-
-
-
-
-
-
(Locked)
Module 4: Applications of foundation models introduction41s
-
(Locked)
Learning objectives34s
-
(Locked)
Pretrained model selection criteria5m
-
(Locked)
Model inference parameters3m 54s
-
Introduction to RAG5m 1s
-
(Locked)
Introduction to vector databases4m 15s
-
(Locked)
AWS vector database service3m 16s
-
(Locked)
Foundation model customization cost tradeoffs3m 16s
-
(Locked)
Generative AI agents5m 17s
-
(Locked)
Question breakdown, part 12m
-
(Locked)
Question breakdown, part 22m 50s
-
(Locked)
-
-
-
-
-
-
-
-