Mastering Generative AI and LLM Deployment. (Udemy.com)

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 Python Programming Languagess. Candidates will have practical lab exercies based on Small LLM training, Quaantization and Deployment stages. Candidates will develop all END-END LLM Applications, starting from training till Deployment Quaantization Fase.

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 FLASK
Here 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

• BERT 101, Distil BERT

• FINE-Tuning Small Models under supervision of BIG Models

Image Generation :

1. LLAMA models

2. Gemini

3. Dall-E OpenAI

4. Hugging face Models

Quantization Techniques and Principles:

1. Lora and Qlora

2. TensorRT principles

3. All Possible Quantizization Techniques.

1. Learning and Installation of Docker from scratch

2. Knowledge of Javscript, HTML ,CSS, Bootstrap

3. React Hook, DOM and Javacscript Web Development

4. Deep Dive on Deep Learning Transformer based Natural Language Processing

5. Python FLASK  Rest API along with MySql

6. Preparation of DockerFiles, Docker Compose as well as Docker Compose Debug file

7. Configuration and Installation of Plugin packages in Visual Studio Code

8. Learning, Installation and Confguration of frameworks such as Tensorflow, Pytorch, Kears with docker images from scratch

9. Preprocessing and Preparation of Deep learning datasets for training and testing

10. OpenCV  DNN with C++ Inference

11. Training, Testing and Validation of Deep Learning frameworks

12. Conversion of prebuilt models to Onnx  and Onnx Inference on images with C++ Programming

13. Conversion of onnx model to TensorRT engine with C++ RunTime and Compile Time API

14. TensorRT engine Inference on images and videos

15. Comparison of achieved metrices and result between TensorRT and Onnx Inference

16. Prepare Yourself for C++ Object Oriented Programming Inference!

17. Ready to solve any programming challenge with C/C++

18. Read to tackle Deployment issues on Edge Devices as well as Cloud Areas

19. Large Language Models Fine Tunning

20. Large Language Models Hands-On-Practice: BLOOM, GPT3-GPT3.5, FLAN-T5 family

21. Large Language Models Training, Evaluation and User-Defined Prompt IN-Context Learning/On-Line Learning

22. Human FeedBack Alignment on LLM with Reinforcement Learning (PPO) with Large Language Model : BERT and FLAN-T5

23. How to Avoid Catastropich Forgetting Program on Large Multi-Task LLM Models.

24. How to prepare LLM for Multi-Task Problems such as Code Generation, Summarization, Content Analizer, Image Generation.

25. 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.