Training
DSCI-273: Generative AI on Cloudera
Overview
Generative AI (GenAI) and Large Language Models (LLMs) are extremely powerful new tools that are changing every industry. To fully take advantage of GenAI and LLMs, these new capabilities need to be combined with your existing enterprise data. This two-day course teaches how to use Cloudera AI to train, augment, fine tune, and host LLMs to create powerful enterprise AI solutions.
What you'll learn
Through lecture and Hands-On exercises, you will learn how to:
- Select the right LLM model for a use case
- Configure a Prompt for an LLM
- Use Retrieval Augmented Generation (RAG)
- Fine Tune an LLM Model with Enterprise Data
- Use the AI Model Registry and host an LLM
- Create an AI Agent with Crew AI
Who should take this course?
This course is designed for data scientists and machine learning engineers who need to understand how to utilize Cloudera AI to leverage the full power of their enterprise data, generative AI, and Large Language Models and deliver powerful business solutions.
Other Training That Might Interest You
- Introducing Python
- Introducing Git
Book the course
Course Details
Introduction to LLMs
History of LLMs
How Transformers Work
Different Types of LLMs
Limitations of LLMs
LLM Model Selection
How LLMs are Evaluated
Model Selection by Use Case
Hugging Face Model Hub
Hands-On Exercise: Open LLM Leaderboard
Hands-On Exercise: Can you run it? LLM Version
Model Registries and Inference Services
Cloudera AI Model Registry
AI Inference Service
Hands-On Exercise: Text Summarization with Amazon Bedrock
Prompt Engineering
Components of a Prompt
Shot Prompting
Hands-On Exercise: Prompt Engineering with Mistral
Retrieval Augmented Generation
Retrieval Augmented Generation (RAG)
RAG Use Cases
Hands-On Exercise: LLM Chatbot Augmented with Enterprise Data
Hands-On Exercise: Intelligent QA Chatbot with NiFi, Pinecode, and Llama2
Fine Tuning
Motivation for Fine Tuning
Principles of Fine Tuning
Parameter Efficient Tuning
Limitations of Fine Tuning
Principles of Parameter Efficient Tuning
Fine Tuning a Foundation Model
Quantization
Low Rank Adaptation
Hands-On Exercise: Fine Tuning a Foundation Model for Multiple Tasks (with QLoRA)
AI Agents
Introduction to AI Agents
AI Agent Architecture
Hands-On Exercise: All Your Agents with Crew AI