Large Language Models (LLMs) are AI models trained on vast amounts of text data to understand, generate, and process human-like language. They power applications like chatbots, text summarization, code generation, and much more.
Week-1. Introduction to Large Language Models
Evolution of LLMs, Use Cases, Ethical Considerations
Week-2.Transformers & Self-Attention
Attention Mechanism, Positional Encoding, Multi-Head Attention
Week-3. Tokenization & Embeddings
WordPiece, BPE, SentencePiece, Tokenizers
Week-4. Understanding Pre-trained LLMs
GPT, BERT, LLaMA, Mistral, Claude, Gemini
Week-5. Fine-Tuning LLMs
LoRA, PEFT, RLHF, Domain-Specific Fine-Tuning
Week-6.Parameter Efficient Fine-Tuning (PEFT)
Adapters, Prefix-Tuning, BitFit
Week-7. Effective Prompt Engineering
Zero-Shot, Few-Shot, Chain-of-Thought (CoT), RAG
Week-8. Memory-Augmented LLMs
Retrieval-Augmented Generation (RAG), LangChain
Week-9.Handling LLM Hallucinations & Bias
Fact-Checking, Safety Mechanisms
Week-10. Building LLM APIs
FastAPI, Hugging Face Inference, OpenAI API
Week-11. Vector Databases & Memory
FAISS, Pinecone, ChromaDB
Week-12. Deploying LLMs on Cloud
AWS, GCP, Azure, Hugging Face Spaces
Week-13. LLMs in Autonomous Agents
AutoGPT, BabyAGI, Agentic AI
Week-14. Security & Privacy in LLMs
Data Leakage, Adversarial Attacks, Mitigation Strategies
Week-15.Capstone Project – Part 1
LLM Selection, Data Preparation
Week-16. Capstone Project – Part 2
Fine-Tuning, Deployment, Optimization