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/lcs2-iiitd/monteclora

공식 코드

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation

https://github.com/leaplabthu/cross-modal-adapter

공식 코드

Cross-Modal Adapter for Text-Video Retrieval

https://github.com/leiluk1/codesearcher

공식 코드

Refining Joint Text and Source Code Embeddings for Retrieval Task with Parameter-Efficient Fine-Tuning

https://github.com/leo-yangli/vb-lora

공식 코드

VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

https://github.com/leopold1423/non_zero_lora-icml25

공식 코드

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

https://github.com/liangyanshuo/InfLoRA

공식 코드

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning

https://github.com/liangyanshuo/gainlora

공식 코드

Gated Integration of Low-Rank Adaptation for Continual Learning of Language Models

https://github.com/liar406/gui-lomo

공식 코드

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

https://github.com/lin-tianwei/teamlora

공식 코드

TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition

https://github.com/lins-lab/capaboost

공식 코드

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

https://github.com/linziyi96/st-adapter

공식 코드

ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning

https://github.com/litinglin/lorat

공식 코드

Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

https://github.com/little0o0/quaff

공식 코드

Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis

https://github.com/liuqidong07/moelora-peft

공식 코드

When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications

https://github.com/liuting20/sparse-tuning

공식 코드

Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference

https://github.com/lizhepolyu/spectralft

공식 코드

Spectral-Aware Low-Rank Adaptation for Speaker Verification

https://github.com/lliutianc/roselora

공식 코드

RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning

https://github.com/lucius-lsr/adaptergnn

공식 코드

AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs

https://github.com/lucky-lance/spp

공식 코드

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

https://github.com/lunaproject22/rpa

공식 코드

RCA: Region Conditioned Adaptation for Visual Abductive Reasoning

https://github.com/mamadou-keita/deeclip

공식 코드

DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images

https://github.com/manncodes/domain-expansion

공식 코드

Domain Expansion: Parameter-Efficient Modules as Building Blocks for Composite Domains

https://github.com/maoyangou147/ts-sam

공식 코드

TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks

https://github.com/martin-wey/peft-llm-code

공식 코드

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

https://github.com/masakhane-io/masakhane-news

공식 코드

MasakhaNEWS: News Topic Classification for African languages

https://github.com/masakhane-io/masakhane-pos

공식 코드

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

https://github.com/matthewkkai/malp

공식 코드

LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination

https://github.com/matthewkkai/milp

공식 코드

Personalized LLM Response Generation with Parameterized Memory Injection

https://github.com/maxwellyaoni/pace

공식 코드

PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization

https://github.com/mdausort/Cytology-fine-tuning

공식 코드

Exploring Foundation Models Fine-Tuning for Cytology Classification

https://github.com/mecuping/dlp-lora

공식 코드

DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models

https://github.com/mediabrain-sjtu/disam

공식 코드

Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts

https://github.com/michalspiegel/imgtb

공식 코드

KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection

https://github.com/microsoft/AdaMix

공식 코드

AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning

https://github.com/microsoft/LoRA

공식 코드

LoRA: Low-Rank Adaptation of Large Language Models

https://github.com/microsoft/list

공식 코드

LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners

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