LLM Basics

- AI/ML Enthusiasts interested in learning about NLP (Natural Language Processing) and Large Language Models (LLMs).

- Data Scientists/Engineers interesting in using LLMs for inference and finetuning

- Software Developers wanting basic practical experience with NLP frameworks and LLMs

- Students and Professionals curious about the basics of transformers and how they power AI models

Working with an engaging, hands-on learning environment, and guided by  an expert instructor, students will learn the basics of Large Language Models (LLMs) and how to use them for inference to build AI powered applications.    

• Understand the basics of Natural Language Processing   
• Implement text preprocessing and tokenization techniques using NLTK   
• Explain word embeddings and the evolution of language models   
• Use RNNs and LSTMs for handling sequential data   
• Describe what transformers are and use key models like BERT and GPT   
• Understand the risks and limitations of LLMs   
• Use pre-trained models from Hugging Face to implement NLP tasks   
• Understand the basics of Retrieval-Augmented Generation (RAG) systems

1) Introduction to NLP   

• What is NLP?  
• NLP Basics: Text Preprocessing and Tokenization  
• NLP Basics: Word Embeddings  
• Introducing Traditional NLP Libraries  
• A brief history of modeling language  
• Introducing PyTorch and HuggingFace for Text Preprocessing  
• Neural Networks and Text Data  
• Building Language Models using RNNs and LSTMs 

2) Transformers and LLMs   

• Introduction to Transformers  
• Using Hugging Face’s Transformers for inference   
• LLMs and Generative AI  
• Current LLM Options   
• Fine tuning GPT  
• Aligning LLMs with Human Values   
• Retrieval-Augmented Generation (RAG) Systems
  

• Proficiency in Python programming
• Familiarity with data analysis using Pandas