Foundation Models vs Task-Specific Models

Limitations, Bias, and Ethics of LLMs

Context Window and Its Limitations

Zero-Shot, One-Shot, Few-Shot Learning

Prompting and Prompt Engineering Basics

Reinforcement Learning from Human Feedback

Fine-Tuning and Instruction Tuning

Pretraining on Large Text Corpora

Next-Token Prediction and Autoregressive Generation

Embeddings in LLMs

Tokens and Tokenization in LLMs

Self-Attention Mechanism Intuition

The Transformer Architecture Overview

What a Large Language Model Is

Generative vs Discriminative AI

Real-World Applications of LLMs

Generative Models Beyond Text

Model Parameters and Scaling Laws

Retrieval-Augmented Generation (RAG)

Hallucinations and Factual Reliability

Decoding: Temperature, Top-k, Top-p

Retrieval-Augmented Generation (RAG)

What a Large Language Model Is

Fine-Tuning Pretrained Models

Prompt Engineering Basics

Reinforcement Learning from Human Feedback

Context Window and Token Limits

Chain-of-Thought Prompting

Diffusion Models for Image Generation

Positional Encoding

Next-Token Prediction Objective

In-Context Learning

Discriminative vs Generative Models

Zero-Shot vs Few-Shot Prompting

Self-Attention Mechanism

Variational Autoencoders (VAEs)

Instruction Tuning

Foundation Models Concept

Generative Adversarial Networks (GANs)

Text Generation Decoding Strategies

Encoder vs Decoder vs Encoder-Decoder

Evaluating Generative Model Outputs

What Generative AI Is

Hallucinations in LLMs

The Transformer Architecture

Model Parameters and Scale

Temperature and Sampling Parameters

Prompt Injection and Adversarial Prompts

Practical Applications of Generative AI

Parameter-Efficient Fine-Tuning (LoRA)

Multimodal Generative Models

Emergent Abilities in Large Models

Scaling Laws for LLMs

Pretraining LLMs on Large Corpora

Instruction Tuning

Greedy vs Beam Search Decoding

System Prompts and Role Instructions

Zero, One, and Few-Shot Prompting

Top-k and Top-p Sampling

In-Context Learning

Retrieval-Augmented Generation (RAG)

RLHF

Chain-of-Thought Prompting

Temperature and Sampling Parameters

Hallucinations in LLMs

Embeddings and Vector Databases

Prompt Injection and Safety

Parameter-Efficient Fine-Tuning

Text-to-Image and Multimodal Models

Fine-tuning vs Prompting vs RAG

Generative Adversarial Networks

Encoder, Decoder, and Encoder-Decoder

Foundation Models Concept

Knowledge Cutoff and Model Staleness

Limitations and Risks of LLMs

Diffusion Models

Evaluating Generative Models

Next-Token Prediction Objective

Emergent Abilities and Scaling Laws

What is a Large Language Model

Tokenization (Subword/BPE)

What is Generative AI

Prompt Engineering Basics

Pre-training vs Fine-tuning

Model Parameters and Scale

Autoregressive Text Generation

Discriminative vs Generative Models

Context Window

Self-Supervised Learning for LLMs