What Is Sales Analytics and How Does It Benefit My Business?
March 4, 2024
Article
This course is part of multiple programs.
Instructors: Joseph Santarcangelo
3,584 already enrolled
Included with
(34 reviews)
Recommended experience
Intermediate level
Basic knowledge of LLMs, instruction-tuning, and reinforcement learning. Familiarity with machine learning and neural network concepts.
(34 reviews)
Recommended experience
Intermediate level
Basic knowledge of LLMs, instruction-tuning, and reinforcement learning. Familiarity with machine learning and neural network concepts.
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
Add to your LinkedIn profile
October 2024
5 assignments
Add this credential to your LinkedIn profile, resume, or CV
Share it on social media and in your performance review
Fine-tuning a large language model (LLM) is crucial for aligning it with specific business needs, enhancing accuracy, and optimizing its performance. In turn, this gives businesses precise, actionable insights that drive efficiency and innovation. This course gives aspiring gen AI engineers valuable fine-tuning skills employers are actively seeking.
During this course, you’ll explore different approaches to fine-tuning and causal LLMs with human feedback and direct preference. You’ll look at LLMs as policies for probability distributions for generating responses and the concepts of instruction-tuning with Hugging Face. You’ll learn to calculate rewards using human feedback and reward modeling with Hugging Face. Plus, you’ll explore reinforcement learning from human feedback (RLHF), proximal policy optimization (PPO) and PPO Trainer, and optimal solutions for direct preference optimization (DPO) problems. As you learn, you’ll get valuable hands-on experience in online labs where you’ll work on reward modeling, PPO, and DPO. If you’re looking to add in-demand capabilities in fine-tuning LLMs to your resume, ENROLL TODAY and build the job-ready skills employers are looking for in just two weeks!
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.
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
10 videos5 readings3 assignments2 app items4 plugins
At IBM, we know how rapidly tech evolves and recognize the crucial need for businesses and professionals to build job-ready, hands-on skills quickly. As a market-leading tech innovator, we’re committed to helping you thrive in this dynamic landscape. Through IBM Skills Network, our expertly designed training programs in AI, software development, cybersecurity, data science, business management, and more, provide the essential skills you need to secure your first job, advance your career, or drive business success. Whether you’re upskilling yourself or your team, our courses, Specializations, and Professional Certificates build the technical expertise that ensures you, and your organization, excel in a competitive world.
Specialization
Specialization
DeepLearning.AI
Course
Unlimited access to 10,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription
Earn a degree from world-class universities - 100% online
Upskill your employees to excel in the digital economy
It takes about 3–5 hours to complete this course, so you can have the job-ready skills you need to impress an employer within just two weeks!
This course is intermediate level, so to get the most out of your learning, you must have basic knowledge of Python, large language models (LLMs), reinforcement learning, and instruction-tuning. You should also be familiar with machine learning and neural network concepts.
This course is part of the Generative AI Engineering with LLMs specialization. When you complete the specialization, you will have the skills and confidence to take on job roles such as AI engineer, data scientist, machine learning engineer, deep learning engineer, AI engineer, and developers seeking to work with LLMs.
Only a modern web browser is required to complete this course and all hands-on labs. You will be provided access to cloud-based environments to complete the labs at no charge.
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
If you subscribed, you get a 7-day free trial during which you can cancel at no penalty. After that, we don’t give refunds, but you can cancel your subscription at any time. See our full refund policy.