Papers with Code 아카이브

parameter-efficient fine-tuning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/savadikarc/gift

공식 코드

Generative Parameter-Efficient Fine-Tuning

https://github.com/sayankotor/sparse_grads

공식 코드

SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers

https://github.com/scale-lab/mtlora

공식 코드

MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning

https://github.com/scale-lab/politune

공식 코드

PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models

https://github.com/scarlet0703/LoRA-Sub-DRS

공식 코드

LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning

https://github.com/sdqesdataset/sdqes_generation

공식 코드

Streaming Detection of Queried Event Start

https://github.com/seekerhuang/harma

공식 코드

Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment

https://github.com/segment-any-text/wtpsplit

공식 코드

Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation

https://github.com/selfsupervised-ai/natural-galore

공식 코드

Natural GaLore: Accelerating GaLore for memory-efficient LLM Training and Fine-tuning

https://github.com/shallowdream204/lora-ir

공식 코드

LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration

https://github.com/shamerd/source-code-efficient-ft

공식 코드

Parameter-Efficient Finetuning of Transformers for Source Code

https://github.com/shiluohe/referencetrustabledecoding

공식 코드

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

https://github.com/showlab/sct

공식 코드

SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels

https://github.com/shuaizhao95/Unlearning

공식 코드

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

https://github.com/shudun23/aroma

공식 코드

AROMA: Autonomous Rank-one Matrix Adaptation

https://github.com/shuzhouyuan/gnnavi

공식 코드

GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network

https://github.com/sjtu-deepvisionlab/flora

공식 코드

FLoRA: Low-Rank Core Space for N-dimension

https://github.com/skddj/loldu

공식 코드

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

https://github.com/snalyami/CLIP-SLA

공식 코드

CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition

https://github.com/song-wx/sift

공식 코드

Sparse is Enough in Fine-tuning Pre-trained Large Language Models

https://github.com/songw-zju/pointlora

공식 코드

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

https://github.com/sony/MambaPEFT

공식 코드

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

https://github.com/sprocketlab/sparse_matrix_fine_tuning

공식 코드

MoRe Fine-Tuning with 10x Fewer Parameters

https://github.com/ssfgunner/snell

공식 코드

Expanding Sparse Tuning for Low Memory Usage

https://github.com/surrey-nlp/LLMs4MTQE-UGC

공식 코드

Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?

https://github.com/synbol/awesome-parameter-efficient-transfer-learning

공식 코드

Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey

https://github.com/syyunn/finrl-dt

공식 코드

Pretrained LLM Adapted with LoRA as a Decision Transformer for Offline RL in Quantitative Trading

https://github.com/szc12153/sparse_meta_tuning

공식 코드

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

https://github.com/takahikof/stag

공식 코드

Token Adaptation via Side Graph Convolution for Temporally and Spatially Efficient Fine-tuning of 3D Point Cloud Transformers

https://github.com/tamsiuhin/oppu

공식 코드

Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning

https://github.com/tanganke/peta

공식 코드

Parameter Efficient Multi-task Model Fusion with Partial Linearization

https://github.com/tangyuan96/minigpt-3d

공식 코드

MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors

https://github.com/te4p0t/kind

공식 코드

KIND: Knowledge Integration and Diversion for Training Decomposable Models

https://github.com/theia-4869/mosa

공식 코드

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning

https://github.com/thisisbillhe/efficientdm

공식 코드

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

https://github.com/thu-mig/pyra

공식 코드

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

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