Autocorrelation Matrix Knowledge Distillation: A Task-Specific Distillation Method for BERT Models
Pre-trained language models perform well in various natural language processing tasks. However, their large number of parameters poses significant challenges for edge devices with limited resources, greatly limiting their application in practical deployment. This paper introduces a simple and effici...
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
MDPI AG
2024-10-01
|
| Serie: | Applied Sciences |
| Soggetti: | |
| Accesso online: | https://www.mdpi.com/2076-3417/14/20/9180 |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|