kaushikacharya / generative_ai_with_llm

Coursera course: Generative AI with Large Language Models

Generative AI with Large Language Models

Course Info

• URL

Course Contents

Chapter #	Chapter
1	Introduction to LLMs and generative AI project lifecycle
2	LLM pre-training and scaling laws
3	Fine-tuning LLMs with instruction
4	Parameter Efficient Fine-Tuning
5	Reinforcement Learning from Human Feedback
6	LLM-powered applications
7	Course conclusion and ongoing research

Lab assignments

Lab #	Assignment	Description
1	Generative AI Use Case: Summarize Dialogue	Perform prompt engineering Compare zero shot, one shot and few shot inferences
2	Fine-Tune a Generative AI Model for Dialogue Summarization	Perform full fine-tuning and PEFT Evaluate results with ROUGE metrics
3	Fine-Tune FLAN-T5 with Reinforcement Learning (PPO) and PEFT to Generate Less-Toxic Summaries	Fine-tune a FLAN-T5 model to generate less toxic summary Use Meta AI's RoBERTa-based hate speech model for the reward model Use Proximal Policy Optimization (PPO) to fine-tune and reduce the model's toxicity

FAQs

• GenAI with LLMs lab FAQ

Lecture Notes

• Notes

Certificate

• Course completion certificate
• Issued on Jan 2024