Training and post-training
LoRA / QLoRA
Parameter-efficient fine-tuning methods that train small low-rank adapters while keeping base weights frozen. QLoRA combines adapters with a quantized base model to reduce memory use further.
Key terms
- low-rank adapters
- frozen base model
- 4-bit training
- PEFT
Connected across the project
Used by
Related technology
Related papers
Historical context
Primary sources
This is a curated technical map, not a claim of comprehensive coverage.