https://github.com/thu-ml/hide-prompt
공식 코드Towards a General Framework for Continual Learning with Pre-training
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/thudm/awesome-parameter-efficient-fine-tuning-for-foundation-models
공식 코드https://github.com/timdettmers/bitsandbytes
공식 코드https://github.com/tingyu215/routing_vlpeft
공식 코드https://github.com/tjvsonsbeek/open-ended-medical-vqa
공식 코드Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
https://github.com/tommy-xq/sa2vp
공식 코드https://github.com/tsly123/freqfit
공식 코드Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation
https://github.com/txchen-ustc/llama-slayer
공식 코드Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
https://github.com/tyang816/ses-adapter
공식 코드Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language Models
https://github.com/ucwxb/i-medsam
공식 코드I-MedSAM: Implicit Medical Image Segmentation with Segment Anything
https://github.com/uds-lsv/afro-maft
공식 코드Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning
https://github.com/uijeongjang/lora-ntk
공식 코드LoRA Training in the NTK Regime has No Spurious Local Minima
https://github.com/umbertocappellazzo/petl_ast
공식 코드Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
https://github.com/uw-madison-lee-lab/expressive_power_of_lora
공식 코드https://github.com/vengdeng/darex
공식 코드DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
https://github.com/vermouthdky/simteg
공식 코드SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning
https://github.com/vijaylingam95/svft
공식 코드https://github.com/visionxlab/earth-adapter
공식 코드Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation
https://github.com/vita-group/dsee
공식 코드DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
https://github.com/vita-group/tape
공식 코드Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding
https://github.com/vt-nlp/mixlora
공식 코드Multimodal Instruction Tuning with Conditional Mixture of LoRA
https://github.com/vvorakit/Entity-Aspect-Sentiment-Triplet-Extraction
공식 코드Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation Models
https://github.com/wangangcheng/lora-pt
공식 코드https://github.com/wengbenjue/llms-peft-cook
공식 코드https://github.com/wenlai-lavine/jola
공식 코드Joint Localization and Activation Editing for Low-Resource Fine-Tuning
https://github.com/wenruicai/spmtrack
공식 코드https://github.com/willemsenbram/mention-detection-vgd
공식 코드Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
https://github.com/willhawkins3/finetuningtoxicity
공식 코드https://github.com/williamgazeley/confirm
공식 코드https://github.com/woosunghyeon/dropbp
공식 코드DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
https://github.com/world1tree/SpeechTranslationRefinement
공식 코드https://github.com/wssun/promptcs
공식 코드https://github.com/wuyongjiancode/sdpt
공식 코드SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-Language Pre-trained Models
https://github.com/wzh0120/sam2-unet
공식 코드SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
https://github.com/xhanxu/most
공식 코드MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
https://github.com/xlgsyzp/cvpt
공식 코드CVPT: Cross-Attention help Visual Prompt Tuning adapt visual task
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.