Projects
LLM Engineering
LLaMA Factory Fine-tuning Pipeline
A fine-tuning pipeline study covering dataset preparation, supervised fine-tuning, LoRA-style adaptation, and evaluation.
Core Idea
Turn LLM fine-tuning from isolated commands into a reproducible engineering pipeline.
Learning Outcome
Learn the moving pieces behind SFT, LoRA, QLoRA, and preference optimization workflows.
Tags
LLMFine-tuningSFTLoRA
Stack
PythonPyTorchLLaMA Factory
Related Papers
LoRAQLoRADPO