Generative AI Engineering with LLMs Specialization

Generative AI Engineering with LLMs Specialization

Name: Generative AI Engineering with LLMs
Rating: 4.596774193548387 (41 reviews)

Advance your ML career with Gen AI and LLMs . Master the essentials of Gen AI engineering and large language models (LLMs) in just 3 months.

Instructors: Sina Nazeri

What you'll learn

In-demand, job-ready skills in gen AI, NLP apps, and large language models in just 3 months.
How to tokenize and load text data to train LLMs and deploy Skip-Gram, CBOW, Seq2Seq, RNN-based, and Transformer-based models with PyTorch
How to employ frameworks and pre-trained models such as LangChain and Llama for training, developing, fine-tuning, and deploying LLM applications.
How to implement a question-answering NLP system by preparing, developing, and deploying NLP applications using RAG.

Details to know

Shareable certificate

Add to your LinkedIn profile

Taught in English

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

Learn more about Coursera for Business

Advance your subject-matter expertise

Learn in-demand skills from university and industry experts
Master a subject or tool with hands-on projects
Develop a deep understanding of key concepts
Earn a career certificate from IBM

Earn a career certificate

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

Share it on social media and in your performance review

Specialization - 7 course series

The Gen AI market is expected to grow 46% . yearly till 2030 (Source: Statista). Gen AI engineers are high in demand. This program gives aspiring data scientists, machine learning engineers, and AI developers essential skills in Gen AI, large language models (LLMs), and natural language processing (NLP) employers need.

Gen AI engineers design systems that understand human language. They use LLMs and machine learning to build these systems.

During this program, you will develop skills to build apps using frameworks and pre-trained foundation models such as BERT, GPT, and LLaMA. You’ll use the Hugging Face transformers library, PyTorch deep learning library, RAG and LangChain framework to develop and deploy LLM NLP-based apps. Plus, you’ll explore tokenization, data loaders, language and embedding models, transformer techniques, attention mechanisms, and prompt engineering.

Through the series of short-courses in this specialization, you’ll also gain practical experience through hands-on labs and a project, which is great for interviews.

This program is ideal for gaining job-ready skills that GenAI engineers, machine learning engineers, data scientists and AI developers require. Note, you need a working knowledge of Python, machine learning, and neural networks.. Exposure to PyTorch is helpful.

Applied Learning Project

Through the hands-on labs and projects in each course, you will gain practical skills in using LLMs for developing NLP-based applications.

Labs and projects you will complete include:

creating an NLP data loader
developing and training a language model with a neural network
applying transformers for classification, building, and evaluating a translation model
engineering prompts and in-context learning
fine-tuning models
applying LangChain tools
building AI agents and applications with RAG and LangChain

In the final course, you will complete a capstone project, applying what you have learned to develop a question-answering bot through a series of hands-on labs. You begin by loading your document from various sources, then apply text splitting strategies to enhance model responsiveness, and use watsonx for embedding. You’ll also implement RAG to improve retrieval and set up a Gradio interface to construct your QA bot. Finally, you will test and deploy your bot.

Generative AI and LLMs: Architecture and Data Preparation

Course 15 hours4.7 (52 ratings)

What you'll learn

Differentiate between generative AI architectures and models, such as RNNs, Transformers, VAEs, GANs, and Diffusion Models.
Describe how LLMs, such as GPT, BERT, BART, and T5, are used in language processing.
Implement tokenization to preprocess raw textual data using NLP libraries such as NLTK, spaCy, BertTokenizer, and XLNetTokenizer.
Create an NLP data loader using PyTorch to perform tokenization, numericalization, and padding of text data.

Gen AI Foundational Models for NLP & Language Understanding

Course 27 hours4.6 (18 ratings)

What you'll learn

Explain how to use one-hot encoding, bag-of-words, embedding, and embedding bags to convert words to features.
Build and use word2vec models for contextual embedding.
Build and train a simple language model with a neural network.
Utilize N-gram and sequence-to-sequence models for document classification, text analysis, and sequence transformation.

Generative AI Language Modeling with Transformers

Course 38 hours4.5 (13 ratings)

What you'll learn

Explain the concept of attention mechanisms in transformers, including their role in capturing contextual information.
Describe language modeling with the decoder-based GPT and encoder-based BERT.
Implement positional encoding, masking, attention mechanism, document classification, and create LLMs like GPT and BERT.
Use transformer-based models and PyTorch functions for text classification, language translation, and modeling.

Generative AI Engineering and Fine-Tuning Transformers

Course 47 hours

What you'll learn

Sought-after job-ready skills businesses need for working with transformer-based LLMs for generative AI engineering... in just 1 week.
How to perform parameter-efficient fine-tuning (PEFT) using LoRA and QLoRA
How to use pretrained transformers for language tasks and fine-tune them for specific tasks.
How to load models and their inferences and train models with Hugging Face.

Generative AI Advance Fine-Tuning for LLMs

Course 58 hours

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

Fundamentals of AI Agents Using RAG and LangChain

Course 66 hours

What you'll learn

In-demand job-ready skills businesses need for building AI agents using RAG and LangChain in just 8 hours.
How to apply the fundamentals of in-context learning and advanced methods of prompt engineering to enhance prompt design.
Key LangChain concepts, tools, components, chat models, chains, and agents.
How to apply RAG, PyTorch, Hugging Face, LLMs, and LangChain technologies to different applications.

Project: Generative AI Applications with RAG and LangChain

Course 79 hours

What you'll learn

Gain practical experience building your own real-world gen AI application that you can talk about in interviews.
Get hands-on using LangChain to load documents and apply text splitting techniques with RAG and LangChain to enhance model responsiveness.
Create and configure a vector database to store document embeddings and develop a retriever to fetch document segments based on queries.
Set up a simple Gradio interface for model interaction and construct a QA bot using LangChain and an LLM to answer questions from loaded documents.