ScholarGate
Assistent

Methoden vergelijken

Bekijk de geselecteerde methoden naast elkaar; rijen die verschillen zijn gemarkeerd.

Multi-Head Self-Attention×LoRA en PEFT×
VakgebiedDeep learningDeep learning
FamilieMachine learningMachine learning
Jaar van ontstaan20172022
GrondleggerVaswani, A. et al.Hu, E. J. et al.; Lester, B. et al.
TypeAttention mechanism (Transformer core)Parameter-efficient fine-tuning of large pretrained models
Oorspronkelijke bronVaswani, A. et al. (2017). Attention Is All You Need. NeurIPS. link ↗Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. link ↗
AliassenÖz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attentionLoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning
Verwant55
SamenvattingMulti-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.
ScholarGateGegevensset
  1. v1
  2. 2 Bronnen
  3. PUBLISHED
  1. v1
  2. 2 Bronnen
  3. PUBLISHED

Naar zoeken Dia's downloaden

ScholarGateMethoden vergelijken: Self-Attention · LoRA and PEFT. Geraadpleegd op 2026-06-18 via https://scholargate.app/nl/compare