Topic
Fine Tuning
Learn Fine Tuning as a connected topic across chapters, concepts, simulations, and interview reasoning.
10 Concepts7 Articles2h 39m
Overview
Learn Fine Tuning as a connected topic across chapters, concepts, simulations, and interview reasoning.
How this topic helps
Llm
Machine Learning
Ai
Deep Learning
Learning Path in this Topic
Series that contain articles from Fine Tuning. Select a path to filter the article list.
Articles
7 matched articles
Article 1RAG vs Fine-Tuning: When to Use Each (and When to Combine Them)📌 TL;DR Summary
Use RAG when facts change frequently and answers must be source-grounded.
Use fine-tuning when you need stable behavior: tone, format, and domain-specific reasoning.
Use RAG + fine-t31 minArticle 2Fine-Tuning LLMs with LoRA and QLoRA: A Practical Deep-DiveTLDR: LoRA freezes the base model and trains two tiny matrices per layer — 0.1 % of parameters, 70 % less GPU memory, near-identical quality. QLoRA adds 4-bit NF4 quantization of the frozen base, enab31 min
Article 3Fine-Tuning LLMs: The Complete Engineer's Guide to SFT, LoRA, and RLHFTLDR: A pretrained LLM is a generalist. Fine-tuning makes it a specialist. Supervised Fine-Tuning (SFT) teaches it your domain's language through labeled examples. LoRA does the same with 99% fewer tr30 minArticle 4SFT for LLMs: A Practical Guide to Supervised Fine-TuningTLDR: Supervised fine-tuning (SFT) is the stage where a pretrained model learns task-specific response behavior from curated input-output examples. It is usually the first alignment step after pretrai12 minArticle 5PEFT, LoRA, and QLoRA: A Practical Guide to Efficient LLM Fine-TuningTLDR: Full fine-tuning updates every model weight, which is expensive in memory, compute, and storage. PEFT methods update only a small trainable slice. LoRA learns low-rank adapters on top of frozen 14 min
Article 6Transfer Learning Explained: Standing on the Shoulders of Pretrained ModelsTLDR: You don't need millions of labeled images or months of GPU time to build a great model. Transfer learning lets you borrow a pretrained network's hard-won feature detectors, plug in a new output 28 minPage 1 of 2