Loading course…
Loading course…
Created by Anirudh Shrikanth
Learn how modern teams adapt large language models without training from scratch. You’ll practice deciding when to use fine-tuning vs RAG, understand parameter-efficient tuning and quantization at a mechanical level, and finish with evaluation and alignment workflows used in real systems.
6 modules • Each builds on the previous one
Clarify what “fine-tuning” changes in a pretrained LLM, and how instruction tuning differs from prompt engineering (it updates weights to follow instructions reliably). You’ll map common goals (style, tool use, domain language) to the right tuning stage.
Learn how to design instruction-following datasets: prompt/response schemas, diversity, difficulty balancing, deduplication, safety filtering, and train/validation splits. Focus on what actually improves behavior (coverage, consistency, and high-signal examples).
Understand parameter-efficient fine-tuning (PEFT): the base model weights stay frozen, while small modules learn task-specific updates. Connect this to why PEFT is cheaper and often safer than full fine-tuning.
Fix the quantization misconception: quantization changes how weights are stored (e.g., 16-bit → 4-bit), while some computations and adapters often remain higher precision. Then connect this to QLoRA: a 4-bit quantized base model plus trainable LoRA adapters for low-VRAM fine-tuning.
Compare RAG vs fine-tuning trade-offs (freshness, cost, controllability, latency), then learn the core components of RAG: embeddings, chunking, vector indexes, retrieval, and reranking. You’ll understand how a vector database fits into an end-to-end RAG pipeline.
Learn how to evaluate fine-tuned models (perplexity, task metrics, preference/win-rate eval) and how alignment methods build on that: RLHF (reward modeling + policy optimization) versus DPO (a simpler, modern preference-optimization approach). Emphasis is on practical selection and “low effort” implementation paths.
Begin your learning journey
In-video quizzes and scaffolded content to maximize retention.