Vizuara Books
LLM Finetuning
Rewire a pretrained model to your task.
A hands-on tour of finetuning: instruction tuning by hand, then Hugging Face, Unsloth, LoRA, and QLoRA at scale. Closes with research-grade projects on subliminal learning and retrieval-augmented finetuning (RAFT).
Read on your Kindle
We'll send this whole book straight to your Kindle — it opens natively, so you can resize the text, read fully offline, and it remembers where you left off. Nothing to download or manage.
Sending to Kindle is for subscribers — subscribe to read the whole library on your Kindle.
00Why Finetune at All5 capsules
Why Finetune at All — 5 chapters.
01What Finetuning Actually Isconceptfree13 min02Pretraining vs Finetuningconcept🔒12 min03Knowledge vs Behaviorintuition🔒14 min04Transfer Learning and Intrinsic Dimensionalitymath🔒12 min05Who Finetuning Is Forconcept🔒14 min01Finetuning vs RAG6 capsules
Finetuning vs RAG — 6 chapters.
06The Central Tradeoffconcept🔒13 min07How RAG Worksconcept🔒14 min08Structured vs Unstructured RAGconcept🔒12 min09Case Study: A Financial Chatbotproject🔒12 min10The Technical Limits of RAGdeep-dive🔒14 min11Few-Shot Prompting vs Finetuningintuition🔒14 min02Instruction Finetuning from Scratch6 capsules
Instruction Finetuning from Scratch — 6 chapters.
12Anatomy of an Instruction Datasetcode🔒13 min13Tokenizing and Formatting the Datacode🔒14 min14The Finetuning Training Loopcode🔒14 min15Sparse Finetuning and Layer Normsdeep-dive🔒13 min16Evaluating Your Finetuned Modelconcept🔒15 min17How OpenAI Uses Finetuningconcept🔒12 min03Finetuning with Hugging Face & Unsloth7 capsules
Finetuning with Hugging Face & Unsloth — 7 chapters.
18The Hugging Face Ecosystemconcept🔒14 min19Loading and Testing the Tiny Stories Modelcode🔒13 min20Instruction vs Classification Finetuningconcept🔒13 min21Adding a Custom Classification Headcode🔒13 min22Data Collation and Dynamic Paddingcode🔒12 min23Left vs Right Paddingdeep-dive🔒13 min24A Finetuning Project with Unslothproject🔒14 min04Parameter-Efficient Finetuning (PEFT)7 capsules
Parameter-Efficient Finetuning (PEFT) — 7 chapters.
25Why Full Finetuning Hurtsconcept🔒13 min26The LoRA Ideamath🔒13 min27The Math Behind LoRAmath🔒14 min28Implementing LoRA in GPT-2code🔒15 min29The PEFT Training Loopcode🔒16 min30Tuning LoRA Hyperparametersdeep-dive🔒15 min31QLoRA and Quantized Finetuningconcept🔒15 min05Research Projects6 capsules
Research Projects — 6 chapters.
32Replicating a Research Paperproject🔒13 min33Subliminal Learning Explaineddeep-dive🔒13 min34Generating Training Data at Scalecode🔒13 min35Finetuning on the OpenAI Platformproject🔒13 min36RAFT: Retrieval-Augmented Finetuningdeep-dive🔒12 min37Setting Up a RAFT Projectproject🔒14 min06Putting It Together3 capsules
Putting It Together — 3 chapters.
38Choosing Your Finetuning Strategyconcept🔒14 min39The Workshop Code and Resourcescode🔒14 min40Capstone: Ship a Finetuned Modelproject🔒14 minRatings & reviews
No ratings yet. Yours would be the first.