IBM
Generative AI Advance Fine-Tuning for LLMs
IBM

Generative AI Advance Fine-Tuning for LLMs

This course is part of multiple programs.

Joseph Santarcangelo
Ashutosh Sagar
Wojciech 'Victor' Fulmyk

Instructors: Joseph Santarcangelo

Sponsored by MAHE Manipal

1,688 already enrolled

Gain insight into a topic and learn the fundamentals.
4.4

(14 reviews)

Intermediate level

Recommended experience

8 hours to complete
3 weeks at 2 hours a week
Flexible schedule
Learn at your own pace
Gain insight into a topic and learn the fundamentals.
4.4

(14 reviews)

Intermediate level

Recommended experience

8 hours to complete
3 weeks at 2 hours a week
Flexible schedule
Learn at your own pace

What you'll learn

  • In-demand gen AI engineering skills in fine-tuning LLMs employers are actively looking for in just 2 weeks

  • Instruction-tuning and reward modeling with the Hugging Face, plus LLMs as policies and RLHF

  • Direct preference optimization (DPO) with partition function and Hugging Face and how to create an optimal solution to a DPO problem

  • How to use proximal policy optimization (PPO) with Hugging Face to create a scoring function and perform dataset tokenization

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

5 assignments

Taught in English
Recently updated!

October 2024

See how employees at top companies are mastering in-demand skills

Placeholder

Build your subject-matter expertise

This course is available as part of
When you enroll in this course, you'll also be asked to select a specific program.
  • Learn new concepts from industry experts
  • Gain a foundational understanding of a subject or tool
  • Develop job-relevant skills with hands-on projects
  • Earn a shareable career certificate
Placeholder
Placeholder

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV

Share it on social media and in your performance review

Placeholder

There are 2 modules in this course

In this module, you’ll begin by defining instruction-tuning and its process. You’ll also gain insights into loading a dataset, generating text pipelines, and training arguments. Further, you’ll delve into reward modeling, where you’ll preprocess the dataset and apply low-rank adaptation (LoRA) configuration. You’ll also learn to quantify quality responses, guide model optimization, and incorporate reward preferences. You’ll also describe reward trainer, an advanced training technique to train a model, and reward model loss using Hugging Face. The labs, in this module will allow practice on instruction-tuning and reward models.

What's included

6 videos4 readings2 assignments2 app items1 plugin

In this module, you’ll describe the applications of large language models (LLMs) to generate policies and probabilities for generating responses based on the input text. You’ll also gain insights into the relationship between the policy and the language model as a function of omega to generate possible responses. Further, this module will demonstrate how to calculate rewards using human feedback incorporating reward function, train response samples, and evaluate agent’s performance. You’ll also define the scoring function for sentiment analysis using PPO with Hugging Face. You’ll also explain the PPO configuration class for specific models and learning rate for PPO training and how the PPO trainer processes the query samples to optimize the chatbot’s policies to get high-quality responses. This module delves into direct preference optimization (DPO) concepts to provide optimal solutions for the generated queries based on human preferences more directly and efficiently using Hugging Face. The labs in this module provide hands-on practice on human feedback and DPO. Methods like PPO and reinforcement learning are quite involved and could be considered subjects of study on their own. While we have provided some references for those interested, you are not expected to understand them in depth for this course

What's included

10 videos5 readings3 assignments2 app items3 plugins

Instructors

Joseph Santarcangelo
IBM
33 Courses1,706,314 learners

Offered by

IBM

Why people choose Coursera for their career

Felipe M.
Learner since 2018
"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."
Jennifer J.
Learner since 2020
"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."
Larry W.
Learner since 2021
"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."
Chaitanya A.
"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Recommended if you're interested in Data Science

Placeholder

Open new doors with Coursera Plus

Unlimited access to 10,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription

Advance your career with an online degree

Earn a degree from world-class universities - 100% online

Join over 3,400 global companies that choose Coursera for Business

Upskill your employees to excel in the digital economy