NLP & Large Language Models Notes
Subject Overview
How language models work, how to use them, and how to fine-tune them for specific tasks. Six modules trace the road from classical NLP and sequence models through the transformer architecture to working with frontier and open models — prompt engineering, structured outputs and function calling — closing with adaptation techniques and the evaluation and safety practices that responsible deployment requires.
Unit-wise Syllabus
8 units — click WhatsApp below to get the full notes for each
Unit 1: Classical NLP (2 hours)
Tokenization, stemming, TF-IDF, word2vec, GloVe, why embeddings changed everything
Unit 2: Sequence Models (3 hours)
RNNs, LSTMs, the attention mechanism, the road from seq2seq to transformers
Unit 3: Transformers Deep Dive (3 hours)
Self-attention, multi-head attention, positional encoding, reading the 'Attention is All You Need' paper
Unit 4: Working with LLMs (4 hours)
GPT, Claude, Llama and Mistral families, API usage, prompt engineering, structured outputs, function calling
Unit 5: Fine-tuning & Adaptation (4 hours)
Full fine-tuning, LoRA, QLoRA, instruction tuning, when to fine-tune versus prompt versus RAG
Unit 6: Evaluation & Safety (4 hours)
Benchmarks, hallucinations, prompt injection, content safety, bias detection
Unit 7: Tools introduced
Hugging Face transformers, PEFT and TRL, OpenAI / Anthropic / open-source model APIs (Together, Groq, Replicate), Ollama for running local models, LangSmith / Langfuse for LLM observability
Unit 8: Mini-projects
Build a sentiment classifier using a fine-tuned BERT, fine-tune a 7B open-source model on a domain-specific dataset with LoRA, build a chatbot with structured outputs and tool use