[Topic]
Tutorials
Step-by-step implementation guides with working code.
TutorialIntermediate
How to fine-tune an open-weight LLM with LoRA and QLoRA
LoRA freezes the base model and trains a small low-rank update on every linear layer. QLoRA does the same on a 4-bit base model, so it needs much less GPU memory. This tutorial fine-tunes Qwen3-4B-Instruct-2507 with Hugging Face TRL and PEFT, then compares it with the base model on a held-out set and serves the adapter with vLLM.