|
Generative AI has taken the world by storm, and we’re beginning to see the subsequent wave of widespread adoption of AI with the potential for each buyer expertise and utility to be reinvented with generative AI. Generative AI permits you to to create new content material and concepts together with conversations, tales, photos, movies, and music. Generative AI is powered by very giant machine studying fashions which might be pre-trained on huge quantities of information, generally known as basis fashions (FMs).
A subset of FMs known as giant language fashions (LLMs) are educated on trillions of phrases throughout many natural-language duties. These LLMs can perceive, study, and generate textual content that’s almost indistinguishable from textual content produced by people. And never solely that, LLMs also can have interaction in interactive conversations, reply questions, summarize dialogs and paperwork, and supply suggestions. They will energy purposes throughout many duties and industries together with artistic writing for advertising, summarizing paperwork for authorized, market analysis for monetary, simulating medical trials for healthcare, and code writing for software program improvement.
Firms are transferring quickly to combine generative AI into their services and products. This will increase the demand for information scientists and engineers who perceive generative AI and how one can apply LLMs to unravel enterprise use circumstances.
This is the reason I’m excited to announce that DeepLearning.AI and AWS are collectively launching a brand new hands-on course Generative AI with giant language fashions on Coursera’s training platform that prepares information scientists and engineers to develop into specialists in choosing, coaching, fine-tuning, and deploying LLMs for real-world purposes.
DeepLearning.AI was based in 2017 by machine studying and training pioneer Andrew Ng with the mission to develop and join the worldwide AI group by delivering world-class AI training.
DeepLearning.AI teamed up with generative AI specialists from AWS together with Chris Fregly, Shelbee Eigenbrode, Mike Chambers, and me to develop and ship this course for information scientists and engineers who need to discover ways to construct generative AI purposes with LLMs. We developed the content material for this course below the steering of Andrew Ng and with enter from numerous business specialists and utilized scientists at Amazon, AWS, and Hugging Face.
Course Highlights
That is the primary complete Coursera course centered on LLMs that particulars the everyday generative AI challenge lifecycle, together with scoping the issue, selecting an LLM, adapting the LLM to your area, optimizing the mannequin for deployment, and integrating into enterprise purposes. The course not solely focuses on the sensible facets of generative AI but additionally highlights the science behind LLMs and why they’re efficient.
The on-demand course is damaged down into three weeks of content material with roughly 16 hours of movies, quizzes, labs, and additional readings. The hands-on labs hosted by AWS Accomplice Vocareum allow you to apply the strategies instantly in an AWS surroundings supplied with the course and consists of all assets wanted to work with the LLMs and discover their effectiveness.
In simply three weeks, the course prepares you to make use of generative AI for enterprise and real-world purposes. Let’s have a fast have a look at every week’s content material.
Week 1 – Generative AI use circumstances, challenge lifecycle, and mannequin pre-training
In week 1, you’ll look at the transformer structure that powers many LLMs, see how these fashions are educated, and take into account the compute assets required to develop them. Additionally, you will discover how one can information mannequin output at inference time utilizing immediate engineering and by specifying generative configuration settings.
Within the first hands-on lab, you’ll assemble and examine totally different prompts for a given generative activity. On this case, you’ll summarize conversations between a number of individuals. For instance, think about summarizing assist conversations between you and your prospects. You’ll discover immediate engineering strategies, strive totally different generative configuration parameters, and experiment with numerous sampling methods to achieve instinct on how one can enhance the generated mannequin responses.
Week 2 – Effective-tuning, parameter-efficient fine-tuning (PEFT), and mannequin analysis
In week 2, you’ll discover choices for adapting pre-trained fashions to particular duties and datasets via a course of known as fine-tuning. A variant of fine-tuning, known as parameter environment friendly fine-tuning (PEFT), permits you to fine-tune very giant fashions utilizing a lot smaller assets—typically a single GPU. Additionally, you will study in regards to the metrics used to guage and examine the efficiency of LLMs.
Within the second lab, you’ll get hands-on with parameter-efficient fine-tuning (PEFT) and examine the outcomes to immediate engineering from the primary lab. This side-by-side comparability will enable you acquire instinct into the qualitative and quantitative affect of various strategies for adapting an LLM to your area particular datasets and use circumstances.
Week 3 – Effective-tuning with reinforcement studying from human suggestions (RLHF), retrieval-augmented technology (RAG), and LangChain
In week 3, you’ll make the LLM responses extra humanlike and align them with human preferences utilizing a method known as reinforcement studying from human suggestions (RLHF). RLHF is vital to bettering the mannequin’s honesty, harmlessness, and helpfulness. Additionally, you will discover strategies corresponding to retrieval-augmented technology (RAG) and libraries corresponding to LangChain that enable the LLM to combine with customized information sources and APIs to enhance the mannequin’s response additional.
Within the last lab, you’ll get hands-on with RLHF. You’ll fine-tune the LLM utilizing a reward mannequin and a reinforcement-learning algorithm known as proximal coverage optimization (PPO) to extend the harmlessness of your mannequin responses. Lastly, you’ll consider the mannequin’s harmlessness earlier than and after the RLHF course of to achieve instinct into the affect of RLHF on aligning an LLM with human values and preferences.
Enroll Right now
Generative AI with giant language fashions is an on-demand, three-week course for information scientists and engineers who need to discover ways to construct generative AI purposes with LLMs.
Enroll for generative AI with giant language fashions immediately.
— Antje
