Module 15: Introduction to Generative AI
- What makes Generative AI different
- Generative AI pipeline & workflow
- Types of GenAI models (LLMs, Diffusion, GANs, VAEs)
- How hallucinations occur & how to reduce them
Module 16: Understanding Large Language Models
- How LLMs are built
- Training, pre-training & scaling laws
- RLHF (Reinforcement Learning with Human Feedback)
- Evaluating LLM performance
Module 17: Prompt Engineering for Real Applications
- Designing effective prompts
- Zero-shot, few-shot & chain-of-thought prompting
- Prompt decomposition & refinement
- Safety prompts & hallucination reduction
- Tool/function calling prompts
Module 18: Fine-Tuning Modern LLMs
- Supervised Fine Tuning
- PEFT: LoRA, QLoRA & adapter training
- Custom dataset creation
- Fine-tuning LLAMA models
- Evaluating fine-tuned models
Module 19: Working with GenAI APIs
- OpenAI API (GPT, DALL·E, Whisper)
- Google Gemini API
- HuggingFace API workflows
- Meta LLaMA APIs
- Azure OpenAI
- Amazon Bedrock
