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/ferdinandzju/iap

공식 코드

IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting

https://github.com/for-ai/parameter-efficient-moe

공식 코드

Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning

https://github.com/fudanxu/lora-det

공식 코드

Low-Rank Adaption on Transformer-based Oriented Object Detector for Satellite Onboard Processing of Remote Sensing Images

https://github.com/furiosa-ai/ssm-peft

공식 코드

Parameter-Efficient Fine-Tuning of State Space Models

https://github.com/furiosa-ai/ssm-state-tuning

공식 코드

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models

https://github.com/fuzihaofzh/analyzeparameterefficientfinetune

공식 코드

On the Effectiveness of Parameter-Efficient Fine-Tuning

https://github.com/fzuzyb/ASteISR

공식 코드

ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo Image Super-resolution

https://github.com/gair-lab/iisan

공식 코드

IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT

https://github.com/garrulus-project/sam_peft

공식 코드

Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery

https://github.com/gatenlp/peft_fft_multilingual

공식 코드

Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification

https://github.com/gccnlp/light-peft

공식 코드

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning

https://github.com/geoaigroup/GEOAI-ECRS2023/tree/main/Empirical%20Study%20of%20PEFT%20techniques%20for%20Winter%20Wheat%20Segmentation

공식 코드

Empirical Study of PEFT techniques for Winter Wheat Segmentation

https://github.com/geoaigroup/geoai-ecrs2023

공식 코드

Empirical Study of PEFT techniques for Winter Wheat Segmentation

https://github.com/gioannides/gaussian-adaptive-attention

공식 코드

Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalities

https://github.com/gmum/b-lora-xs

공식 코드

Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA

https://github.com/guitaricet/peft_comparison

공식 코드

Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning

https://github.com/guozix/cbbt

공식 코드

Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation

https://github.com/hamid-nasiri/edora

공식 코드

EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition

https://github.com/hangeol/unir

공식 코드

Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs

https://github.com/haoweilou/StyleSpeech_Public

공식 코드

StyleSpeech: Parameter-efficient Fine Tuning for Pre-trained Controllable Text-to-Speech

https://github.com/haoweiz23/ship

공식 코드

Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning

https://github.com/hiyouga/llama-factory

공식 코드

Time Sensitive Knowledge Editing through Efficient Finetuning

https://github.com/holistic-ai/THaMES

공식 코드

THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models

https://github.com/huangowen/rolora

공식 코드

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization

https://github.com/huggingface/setfit

공식 코드

Efficient Few-Shot Learning Without Prompts

https://github.com/hungerpway/adept

공식 코드

ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

https://github.com/hyx1999/quad

공식 코드

QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition

https://github.com/iabhijith/bias-causal-analysis

공식 코드

Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model

https://github.com/ibm/deft

공식 코드

From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers

https://github.com/ibm/dp-tabtransformer

공식 코드

Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers

https://github.com/ibm/safelora

공식 코드

Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models

https://github.com/iboing/corda

공식 코드

CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning

https://github.com/idiap/bayesian-peft

공식 코드

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting

https://github.com/info-ucr/peftleak

공식 코드

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning

https://github.com/intellabs/hardware-aware-automated-machine-learning

공식 코드

Shears: Unstructured Sparsity with Neural Low-rank Adapter Search

https://github.com/intelligent-molecular-systems/llm_finetuning_for_biochemistry

공식 코드

Leveraging Large Language Models for enzymatic reaction prediction and characterization

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