LoRA: Low-Rank Adaptation — Roadmap Step & Resources
How LoRA achieves efficient fine-tuning with low-rank matrices
- Level: beginner
- Estimated time: 1 days
- Roadmap: Fine-Tuning & Model Customization
Before this step
Study resources
- OpenAI API Documentation (Article) — OpenAI's official documentation, including guides on fine-tuning hosted models. Background reading/viewing for: LoRA: Low-Rank Adaptation.
- Hugging Face Documentation (Article) — Official documentation on the PEFT library, including LoRA. Relevant to: LoRA: Low-Rank Adaptation.
Part of
- Parameter-Efficient Fine-Tuning (PEFT/LoRA) — section
- Fine-Tuning & Model Customization roadmap — the full learning path