NLP & LLMs

Natural language processing and large language models

36 chapters across 9 modules

1

Foundations Of NLP

4 chapters

1

What Is NLP & Why Language Is Hard

5 min read

2

Text Preprocessing Fundamentals

6 min read

3

Classical NLP: Bag-of-Words, TF-IDF & Naive Bayes

6 min read

4

The Evolution of NLP: Rules to LLMs

5 min read

2

Word Embeddings And Representations

4 chapters

1

From One-Hot to Dense Embeddings

6 min read

2

Word2Vec: CBOW & Skip-Gram

7 min read

3

GloVe & Evaluating Embeddings

6 min read

4

Contextual Embeddings: Why Static Embeddings Fall Short

6 min read

3

Tokenization And Pretraining Foundations

3 chapters

1

Subword Tokenization: BPE, WordPiece, SentencePiece

7 min read

2

Applying the Transformer to Language

6 min read

3

Pre-training Objectives: MLM vs CLM

8 min read

4

Encoder Models Bert And Friends

4 chapters

1

BERT: Architecture & Masked Language Modeling

5 min read

2

BERT's Pretraining: MLM + NSP, and What Came After

6 min read

3

Fine-Tuning BERT for Downstream Tasks

6 min read

4

The BERT Family: RoBERTa, ALBERT, DistilBERT, ELECTRA

7 min read

5

Decoder Models Gpt And Modern Llms

4 chapters

1

GPT: Architecture & Autoregressive Language Modeling

6 min read

2

Scaling Laws & the GPT Family's Evolution

6 min read

3

In-Context Learning & Emergent Abilities

6 min read

4

The Modern LLM Landscape

6 min read

6

Fine Tuning And Aligning Llms

4 chapters

1

Instruction Tuning

6 min read

2

Parameter-Efficient Fine-Tuning: LoRA & QLoRA

7 min read

3

RLHF & Alignment

8 min read

4

A Practical Fine-Tuning Recipe

6 min read

7

Prompt Engineering

3 chapters

1

Prompting Fundamentals

6 min read

2

Advanced Prompting: Chain-of-Thought & Few-Shot Techniques

7 min read

3

Structured Output & Function Calling

7 min read

8

Rag And Agents

5 chapters

1

Why RAG: The Limits of Parametric Knowledge

6 min read

2

Building a RAG Pipeline

6 min read

3

Advanced RAG Techniques

6 min read

4

Agents & Tool Use

6 min read

5

Multi-Agent Systems

6 min read

9

Evaluation Production And Capstone

5 chapters

1

Evaluating Classical NLP: BLEU, ROUGE, Perplexity

6 min read

2

Evaluating LLMs: Benchmarks, Human Eval, LLM-as-Judge

7 min read

3

LLMs in Production

7 min read

4

Capstone: End-to-End RAG Application

6 min read

5

Where to Go Next

4 min read