Generative AI for Developers | Level 2

Building Intelligent Solutions with Generative AI

Duration

5 Days

Level

Intermediate Level

Design and Tailor this course

As per your team needs

Edit Content

This comprehensive course provides an in-depth exploration of Generative AI and Large Language Models (LLMs). Through a series of modules and hands-on lab exercises, participants will gain a solid understanding of key concepts, tools, and techniques in Generative AI. The course is designed to equip participants with the knowledge and skills necessary to leverage LLMs for various applications, including image generation, language processing, and reinforcement learning.

Edit Content

Developers and software engineers interested in learning GenerativeAI
AI enthusiasts and professionals aiming to build intelligent and innovative solutions
Even Data scientists and machine learning practitioners seeking to enhance their skills in working with OpenAI models

Edit Content

Module 1: Recap of key concepts of Generative AI - 1 hour

A quick recap of Generative AI & LLMs
Transformer Architecture
Working with LangChain
AutoGPT
VAEs for image generation

Module 2: Generative AI for Image Generation - 2 hours

Getting started with Image Generation
Conditional Image Generation based on class labels or text description
Concepts related to Style Transfer
Approaches for GANs
- CycleGAN
- pix2pix

Module 3: Applying Diffusion Models - 5 hours

Understanding OpenAI’s DALL-E Image Generation Process
Building Diffusion Models from Scratch
- Starting with Noise and Progressing to Final Images
- Developing Intuition at Each Step
MidJourney: Demonstration App
Lab(s): DALL-E 2 through Azure OpenAI Services

Module 4: Fine-tuning and Evaluating Large Language Models - 8 hours

Introduction to Large Language Models
Pre-training Large Language Models
Computational Challenges in Training LLMs
Scaling Laws and Compute-Optimal Models
Fine-tuning Techniques
- Instruction Fine-tuning
- Fine-tuning on a Single Task
- Multi-task Instruction Fine-tuning
- Parameter Efficient Fine-tuning (PEFT)
- PEFT Techniques: LoRA and Soft Prompts
Model Evaluation and Benchmarks
- Evaluating Fine-tuned Models
- Introduction to Benchmarks
Fine-tuning Lab Setup on Azure OpenAi Studio
- Lab Exercise Walkthrough
- Finetuning on a given use case

Module 5: Reinforcement Learning and LLM-powered Applications - 4 hours

Introduction
Overview of Fine-tuning Large Language Models
Importance of Aligning Models with Human Values
Reinforcement Learning from Human Feedback (RLHF)
- Introduction to RLHF
- Obtaining Feedback from Humans
- Developing a Reward Model for RLHF
Fine-tuning with Reinforcement Learning
- Fine-tuning Process using RLHF
- Techniques for Optimizing RLHF Performance
- Optional Video: Proximal Policy Optimization
- Addressing Reward Hacking
Scaling Human Feedback
- Challenges and Considerations
- Strategies for Collecting and Incorporating Large-scale Feedback
Evaluation and Assessment
- Methods for Evaluating Fine-tuned Language Models
- Assessing Model Performance in Alignment with Human Values

Module 6: Generative AI Projects and Applications - 4 hours

Applications of Generative Models
- Importance and Usefulness
- Potential Applications
- Text Generation Use Cases
- Audio Synthesis Use Cases
- Text-to-Image Generation
Building NLP Applications using OpenAI API
- Summarization, Text Classification, and Fine-tuning GPT Models
Building Midjourney Clone Application
- Using OpenAI DALL-E and StableDiffusion on Hugging Face
Generative AI Project Lifecycle
Using LLMs in Applications
Interacting with External Applications
Helping LLMs Reason and Plan with Chain-of-Thought
Program-aided Language Models
LLM Application Architectures
Responsible AI Considerations

Module 7: LangChain for LLM Application Development - 3 hours

- Concepts for LangChain Projects
  - Utilizing embeddings and vector data stores
  - Enhancing LangChain performance
- LangChain Framework
  - Taking LLMs out of the box
  - Integrating LLMs into new environments using memories, chains, and agents

Lab Exercise Using LangChain - 5 hours

Developing a question-answering application with LangChain, OpenAI, and Hugging Face Spaces

Edit Content

Should have attended course on “Generative AI for Developers | Level 1” or have an equivalent knowledge

FIND YOUR COURSE

Topics

Brands

Generative AI for Developers | Level 2

Duration

Level

Design and Tailor this course

Quick Links

our Offerings

Get in touch

Sign up for DataCouch Communications

Connect

we'd love to have your feedback on your experience so far