Papers with Code 아카이브

parameter-efficient fine-tuning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 3
보존된 평가 기록: 10

Parameter-Efficient Fine-Tuning (PEFT) is a technique used to adapt pre-trained models to new tasks with minimal changes to the model's parameters. This approach is particularly useful in scenarios where computational resources are limited or when it is desirable to maintain the original model's performance on the initial task.

기법

관련 논문에서 소개한 기법입니다. 이 태스크에서의 평가 여부는 평가 결과에서 확인하세요.

EMEA

Entropy Minimized Ensemble of Adapters, or EMEA, is a method that optimizes the ensemble weights of the pretrained language adapters for each test sentence by minimizing the entropy of its predictions. The intuition behind the method is that a good adapter weight $\alpha$ for a test input $x$ should make the model more confident in its prediction for $x$, that is, it should lead to lower model entropy over the input

Efficient Test Time Adapter Ensembling for Low-resource Language Varieties

SORSA

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.