Krahasoni metodat

	Vetë-vëmendja me shumë koka	LoRA dhe PEFT
Fusha	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning
Viti i origjinës	2017	2022
Krijuesi	Vaswani, A. et al.	Hu, E. J. et al.; Lester, B. et al.
Lloji	Attention mechanism (Transformer core)	Parameter-efficient fine-tuning of large pretrained models
Burimi themelues	Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS.	Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR.
Emërtime të tjera	Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention	LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning
Të lidhura	5	5
Përmbledhja	Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5.	LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.