Learn Everything about Full-Stack Generative AI, LLM MODELS from Udemy

This course is diving into Generative AI State-Of-Art Scientific Challenges. It helps to uncover ongoing problems and develop or customize your Own Large Models Applications. Course mainly is suitable for any candidates(students, engineers,experts) that have great motivation to Large Language Models with Todays-Ongoing Challenges as well as their deeployment with Python Based and Javascript Web Applications, as well as with C/C++ Programming Languages. Candidates will have deep knowledge on TensorFlow , Pytorch, Keras models, HuggingFace with Docker Service.

In addition, one will be able to optimize and quantize TensorRT frameworks for deployment in variety of sectors. Moreover, They will learn deployment of LLM quantized model to Web Pages developed with React, Javascript and FLASKHere you will also learn how to integrate Reinforcement Learning(PPO) to Large Language Model, in order to fine them with Human Feedback based. Candidates will learn how to code and debug in C/C++ Programming languages at least in intermediate level.

LLM Models used:

The Falcon,
LLAMA2,
BLOOM,
MPT,
Vicuna,
FLAN-T5,
GPT2/GPT3, GPT NEOX
..

Learning and Installation of Docker from scratch
Knowledge of Javscript
Ready to solve any programming challenge with C/C++
Read to tackle Deployment issues on Edge Devices as well as Cloud Areas
Large Language Models Fine Tunning
Large Language Models Hands-On-Practice: 5, FLAN-T5 family
Large Language Models Training, Evaluation and User-Defined Prompt IN-Context Learning/On-Line Learning
Human FeedBack Alignment on LLM with Reinforcement Learning (PPO) with Large Language Model : BERT and FLAN-T5
How to Avoid Catastropich Forgetting Program on Large Multi-Task LLM Models.
How to prepare LLM for Multi-Task Problems such as Code Generation, Summarization, Content Analizer, Image Generation.
Quantization of Large Language Models with various existing state-of-art techniques

Importante Note: In this course, there is not nothing to copy & paste, you will put your hands in every line of project to be successfully LLM and Web Application Developer.

You DO NOT need any Special Hardware component. You will be delivering project either on CLOUD or on Your Local Computer.

What's inside

Learning objectives

What is docker and how to use docker
Advance docker usage
What are opencl and opengl and when to use ?
(lab) tensorflow and pytorch installation, configuration with docker
(lab)dockerfile, docker compile and docker compose debug file configuration
(lab)different yolo version, comparisons, and when to use which version of yolo according to your problem
(lab)jupyter notebook editor as well as visual studio coding skills
(lab)learn and prepare yourself for full stack and c++ coding exercies
(lab)tensorrt precision float 32/16 model quantiziation
Key differences:explicit vs. implicit batch size
(lab)tensorrt precision int8 model quantiziation
(lab) visual studio code setup and docker debugger with vs and gdb debugger
(lab) what is onnx framework c plus and how to use apply onnx to your custom c ++ problems
(lab) what is tensorrt framework and how to use apply to your custom problems
(lab) custom detection, classification, segmentation problems and inference on images and videos
(lab) basic c ++ object oriented programming
(lab) advance c ++ object oriented programming
(lab) deep learning problem solving skills on edge devices, and cloud computings with c++ programming language
(lab) how to generate high performance inference models on embedded device, in order to get high precision, fps detection as well as less gpu memory consumption
(lab) visual studio code with docker
(lab) gdb debugger with sonarlite and sonarcube debuggers
(lab) yolov4 onnx inference with opencv c++ dnn libraries
(lab) yolov5 onnx inference with opencv c++ dnn libraries
(lab) yolov5 onnx inference with dynamic c++ tensorrt libraries
(lab) c++(11/14/17) compiler programming exercies
Key differences: opencv and cuda/ opencv and tensorrt
(lab) deep dive on react development with axios front end rest api

(lab) deep dive on flask rest api with react with mysql
(lab) deep dive on text summarization inference on web app
(lab) deep dive on bert (llm) fine tunning and emotion analysis on web app
(lab) deep dive on distributed gpu programming with natural language processing (large language models))
(lab) deep dive on generative ai use cases, project lifecycle, and model pre-training
(lab) fine-tuning and evaluating large language models
(lab) reinforcement learning and llm-powered applications, align fine tunning with user feedback
(lab) quantization of large language models with modern nvidia gpu's
(lab) c++ oop tensorrt quantization and fast inference
(lab) deep dive on hugging face library
(lab)translation ● text summarization ● question answering
(lab)sequence-to-sequence models, only encoder based models, only decoder based models
(lab)define the terms generative ai, large language models, prompt, and describe the transformer architecture that powers llms
(lab)discuss computational challenges during model pre-training and determine how to efficiently reduce memory footprint
(lab)describe how fine-tuning with instructions using prompt datasets can improve performance on one or more tasks
(lab)explain how peft decreases computational cost and overcomes catastrophic forgetting
(lab)describe how rlhf uses human feedback to improve the performance and alignment of large language models
(lab)discuss the challenges that llms face with knowledge cut-offs, and explain how information retrieval and augmentation techniques can overcome these challen
Recognize and understand the various strategies and techniques used in fine-tuning language models for specialized applications.
Master the skills necessary to preprocess datasets effectively, ensuring they are in the ideal format for ai training.
Investigate the vast potential of fine-tuned ai models in practical, real-world scenarios across multiple industries.
Acquire knowledge on how to estimate and manage the costs associated with ai model training, making the process efficient and economic
Distributing computing for (ddp) distributed data parallelization and fully shared data parallel across multi gpu/cpu with pytorch together with retrieval augme
The roberta model was proposed in roberta: a robustly optimized bert pretraining approach
Show more
Show less

What is docker and how to use docker
Advance docker usage
What are opencl and opengl and when to use ?
(lab) tensorflow and pytorch installation, configuration with docker
(lab)dockerfile, docker compile and docker compose debug file configuration
(lab)different yolo version, comparisons, and when to use which version of yolo according to your problem
(lab)jupyter notebook editor as well as visual studio coding skills
(lab)learn and prepare yourself for full stack and c++ coding exercies
(lab)tensorrt precision float 32/16 model quantiziation
Key differences:explicit vs. implicit batch size
(lab)tensorrt precision int8 model quantiziation
(lab) visual studio code setup and docker debugger with vs and gdb debugger
(lab) what is onnx framework c plus and how to use apply onnx to your custom c ++ problems
(lab) what is tensorrt framework and how to use apply to your custom problems
(lab) custom detection, classification, segmentation problems and inference on images and videos
(lab) basic c ++ object oriented programming
(lab) advance c ++ object oriented programming
(lab) deep learning problem solving skills on edge devices, and cloud computings with c++ programming language
(lab) how to generate high performance inference models on embedded device, in order to get high precision, fps detection as well as less gpu memory consumption
(lab) visual studio code with docker
(lab) gdb debugger with sonarlite and sonarcube debuggers
(lab) yolov4 onnx inference with opencv c++ dnn libraries
(lab) yolov5 onnx inference with opencv c++ dnn libraries
(lab) yolov5 onnx inference with dynamic c++ tensorrt libraries
(lab) c++(11/14/17) compiler programming exercies
Key differences: opencv and cuda/ opencv and tensorrt
(lab) deep dive on react development with axios front end rest api
(lab) deep dive on flask rest api with react with mysql
(lab) deep dive on text summarization inference on web app
(lab) deep dive on bert (llm) fine tunning and emotion analysis on web app
(lab) deep dive on distributed gpu programming with natural language processing (large language models))
(lab) deep dive on generative ai use cases, project lifecycle, and model pre-training
(lab) fine-tuning and evaluating large language models
(lab) reinforcement learning and llm-powered applications, align fine tunning with user feedback
(lab) quantization of large language models with modern nvidia gpu's
(lab) c++ oop tensorrt quantization and fast inference
(lab) deep dive on hugging face library
(lab)translation ● text summarization ● question answering
(lab)sequence-to-sequence models, only encoder based models, only decoder based models
(lab)define the terms generative ai, large language models, prompt, and describe the transformer architecture that powers llms
(lab)discuss computational challenges during model pre-training and determine how to efficiently reduce memory footprint
(lab)describe how fine-tuning with instructions using prompt datasets can improve performance on one or more tasks
(lab)explain how peft decreases computational cost and overcomes catastrophic forgetting
(lab)describe how rlhf uses human feedback to improve the performance and alignment of large language models
(lab)discuss the challenges that llms face with knowledge cut-offs, and explain how information retrieval and augmentation techniques can overcome these challen
Recognize and understand the various strategies and techniques used in fine-tuning language models for specialized applications.
Master the skills necessary to preprocess datasets effectively, ensuring they are in the ideal format for ai training.
Investigate the vast potential of fine-tuned ai models in practical, real-world scenarios across multiple industries.
Acquire knowledge on how to estimate and manage the costs associated with ai model training, making the process efficient and economic
Distributing computing for (ddp) distributed data parallelization and fully shared data parallel across multi gpu/cpu with pytorch together with retrieval augme
The roberta model was proposed in roberta: a robustly optimized bert pretraining approach
Show more
Show less

Syllabus

All course summary

Course Github LINK:

https://github.com/fikratgasimovsoftwareengineer/FullStack_Web_APP/tree/main

Please find all projects laying on the repository:

https://github.com/fikratgasimovsoftwareengineer/FullStack_Web_APP

My Github Profile:
https://github.com/fikratgasimovsoftwareengineer/FullStack_Web_APP

Bert Model has been saved within zip folder.

This is pretrained model zip file that contains both pretrained model and tokenizer.Please, unzip it and locate it in local working directory!

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Develops skills and knowledge in Generative AI and Large Language models which are key to tackling real world problems in today's tech industry

Taught by PhD Researcher AI & Robotics Scientist Fikrat Gasimov who is recognized for their work in AI and Robotics Science

Examines various state-of-the-art Generative AI models such as The Falcon, LLAMA2, BLOOM, MPT, Vicuna, FLAN-T5, GPT2/GPT3, GPT NEOX

Provides hands-on practice with Tensorflow, Pytorch, Keras models, HuggingFace with Docker Service to gain practical experience with industry-standard tools

Covers how to quantize TensorRT frameworks for deployment in a variety of sectors, enhancing the efficiency and applicability of models

Teaches how to integrate Reinforcement Learning (PPO) to Large Language Models, enabling learners to customize and fine-tune models based on human feedback

Reviews summary

Full-stack generative ai deployment & optimization

According to students, this course offers comprehensive coverage of full-stack Generative AI, including LLM deployment with Python, JavaScript, and C/C++. Learners frequently highlight the hands-on coding and practical projects, particularly for TensorRT optimization and model quantization for deployment. While the course provides deep insights into various LLM models and advanced topics like Reinforcement Learning with Human Feedback (RLHF), a notable portion of learners found the pace challenging and the prerequisites demanding, especially for those not already proficient in C++ or advanced deep learning concepts. It is consistently praised for connecting theory to real-world, deployable applications.

Fast-paced, potentially trading deep dives for broad coverage.

"While it covers a lot, some advanced topics could benefit from more in-depth explanations and slower pacing for better absorption."

"I felt some modules moved very quickly, requiring me to do significant external research to fully grasp certain concepts."

"It’s a 'mile wide' course – great for an overview of many cutting-edge topics, but don't expect exhaustive detail on every single one."

Covers a wide array of advanced AI and programming concepts.

"The course covers an impressive range of topics, from Docker setup to C++ OOP, and various LLM frameworks like HuggingFace."

"It touches upon many advanced concepts such as RLHF, TensorRT, and distributed GPU programming, which is rare to find in one course."

"I learned about multiple LLM architectures and their fine-tuning, giving me a solid overview of the Generative AI landscape."

Provides extensive hands-on experience in LLM deployment.

"I truly appreciated the 'no copy-paste' approach; it forced me to understand every line of code for full-stack LLM deployment."

"The hands-on projects, especially integrating LLMs with React and Flask, were incredibly valuable and directly applicable to my work."

"I gained practical skills in optimizing and quantizing models with TensorRT, which is crucial for real-world deployment scenarios."

Requires strong foundational knowledge in programming and AI.

"The course assumes a high level of proficiency in C++ and deep learning; I think beginners might find it quite overwhelming."

"I struggled at times with the pace, as it jumps into complex topics quickly without much review of fundamentals."

"You really need solid intermediate C/C++ skills and a good grasp of Python and ML concepts to keep up effectively."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Learn Everything about Full-Stack Generative AI, LLM MODELS with these activities:

Organize Course Materials

Show steps

Organize and prepare your learning materials to improve your understanding and engagement with the course.

Show steps

Gather all materials, including syllabus, notes, assignments, and readings.
Create a system for organizing and storing your materials.
Review materials on a regular to familiarize yourself with the course content.

Read 'Deep Learning for Coders with Fastai and PyTorch'

Show steps

Gain a deeper understanding of deep learning concepts by reading this comprehensive book.

View Deep Learning for Coders with Fastai and... on Amazon

Show steps

Read through the book thoroughly, taking notes and highlighting important concepts.
Work through the exercises and examples provided in the book.
Apply the knowledge gained from the book to your own projects.

Join a Study Group

Show steps

Enhance your understanding through peer collaboration and support.

Show steps

Find or form a study group with fellow classmates or online learners.
Meet regularly to discuss course materials, share perspectives, and work on assignments together.
Engage in group discussions, brainstorming sessions, and peer review.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Practice Docker Commands

Show steps

Reinforce your understanding of Docker commands by completing practice exercises.

Browse courses on Docker

Show steps

Review the Docker documentation and tutorials.
Create a simple Dockerfile and build an image.
Run Docker commands to manage containers.
Troubleshoot common Docker issues.
Experiment with different Docker features.

Learn about TensorRT

Show steps

Enhance your knowledge of TensorRT by following guided tutorials.

Show steps

Find online tutorials or documentation on TensorRT.
Follow the tutorials to install and configure TensorRT.
Learn about TensorRT's key features and capabilities.
Apply TensorRT to your own projects or models.
Engage in online forums or communities to ask questions and learn from others.

Literature on Real-World AI Applications

Show steps

Expand your knowledge of real-world AI applications by compiling a collection of relevant resources.

Show steps

Search for research papers, articles, and case studies on various industries where AI is being applied.
Organize and categorize the resources based on application area or industry.
Summarize the key findings and insights from the resources.
Share your compilation with classmates or online communities.

Build a Custom Web Application

Show steps

Solidify your understanding of web application development by creating your own custom project.

Browse courses on Web Development

Show steps

Plan and design your web application.
Choose appropriate technologies and frameworks.
Implement the front-end and back-end components.
Test and debug your application.
Deploy and maintain your application.

Contribute to Open Source AI Projects

Show steps

Gain practical experience and contribute to the AI community by working on open source projects.

Browse courses on Open Source

Show steps

Identify open source AI projects that align with your interests and skills.
Read the project documentation and familiarize yourself with the codebase.
Start contributing by fixing bugs, implementing new features, or improving documentation.
Engage with the project community through online forums or discussions.

Career center

Learners who complete Learn Everything about Full-Stack Generative AI, LLM MODELS will develop knowledge and skills that may be useful to these careers:

Reading list

We haven't picked any books for this reading list yet.

Learn Everything about Full-Stack Generative AI, LLM MODELS

What's inside

Learning objectives

Syllabus

Traffic lights

Save this course

Reviews summary

Full-stack generative ai deployment & optimization

Activities

Career center

Reading list

Share

Similar courses