https://github.com/microsoft/lmops
공식 코드Improving Domain Adaptation through Extended-Text Reading Comprehension
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/microsoft/mttl
공식 코드https://github.com/mikecovlee/DynMoLE
공식 코드DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
https://github.com/mikumikumi0116/dora
공식 코드DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution
https://github.com/mileswyn/samihs
공식 코드SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation
https://github.com/misonsky/HiFT
공식 코드https://github.com/mklimasz/transferable-modularity
공식 코드Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation
https://github.com/ml-jku/EVA
공식 코드Parameter Efficient Fine-tuning via Explained Variance Adaptation
https://github.com/ml-stat-Sustech/CLIP_Calibration
공식 코드https://github.com/mlwu22/red
공식 코드Advancing Parameter Efficiency in Fine-tuning via Representation Editing
https://github.com/moeinsorkhei/apla
공식 코드Efficient Self-Supervised Adaptation for Medical Image Analysis
https://github.com/mohammad-mozaffari/slim
공식 코드SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
https://github.com/mohammadrezabanaei/lora-xs
공식 코드LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
https://github.com/mohammedsb/dinov2formedical
공식 코드https://github.com/mohammedsb/dinov2forradiology
공식 코드https://github.com/morelife2017/alphalora
공식 코드AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality
https://github.com/mrflogs/LoRA-Pro
공식 코드https://github.com/mtkresearch/taste-spokenlm
공식 코드TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
https://github.com/nasosger/mutor
공식 코드https://github.com/nbasyl/DoRA
공식 코드https://github.com/nifangbaage/explicit-visual-prompt
공식 코드Explicit Visual Prompting for Universal Foreground Segmentations
https://github.com/nkuhealong/dvpt
공식 코드DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis
https://github.com/nlpforua/zno
공식 코드Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks
https://github.com/nlpfreshman0/more
공식 코드MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning
https://github.com/noahsark/da-vpt
공식 코드DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
https://github.com/noahsark/parameterefficient-dml
공식 코드https://github.com/nus-hpc-ai-lab/dynamic-tuning
공식 코드Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
https://github.com/nvidia/nemo-aligner
공식 코드NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment
https://github.com/oblivioniss/msplora
공식 코드MSPLoRA: A Multi-Scale Pyramid Low-Rank Adaptation for Efficient Model Fine-Tuning
https://github.com/oceanoceanna/LLMEraser
공식 코드https://github.com/ohsngjun/PEVC
공식 코드Parameter-Efficient Instance-Adaptive Neural Video Compression
https://github.com/om-ai-lab/rs5m
공식 코드https://github.com/opengptx/illuminer
공식 코드ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler
https://github.com/openlmlab/collie
공식 코드CoLLiE: Collaborative Training of Large Language Models in an Efficient Way
https://github.com/openlmlab/lomo
공식 코드Full Parameter Fine-tuning for Large Language Models with Limited Resources
https://github.com/optimalscale/lmflow
공식 코드LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.