parameter-efficient-learning 开源项目推荐（28 个）

huggingface /peft

PEFT：最先进的参数高效微调。

adapter-hub /adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

THUDM /P-tuning-v2

优化的深度即时调优策略，与跨规模和任务的微调相当

thunlp /OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

THUDM /P-tuning

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

OpenBMB /CPM-Live

Live Training for Open-source Big Models

jianghaojun /Awesome-Parameter-Efficient-Transfer-Learning

A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.

HenryHZY /Awesome-Multimodal-LLM

Research Trends in LLM-guided Multimodal Learning.

calpt /awesome-adapter-resources

Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning

LeapLabTHU /Cross-Modal-Adapter

[Pattern Recognition 2025] Cross-Modal Adapter for Vision-Language Retrieval

joaopauloschuler /k-neural-api

K-CAI NEURAL API - Keras based neural network API that will allow you to create parameter-efficient, memory-efficient, flops-efficient multipath models with new layer types. There are plenty of examples and documentation.

juyongjiang /CodeUp

CodeUp: A Multilingual Code Generation Llama-X Model with Parameter-Efficient Instruction-Tuning

ga642381 /Speech-Prompts-Adapters

This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.

thunlp /Prompt-Transferability

On Transferability of Prompt Tuning for Natural Language Processing

fyzhang1 /FocusGUI

Official code for "Focused Omni-Modal GUI Agents“

Paranioar /UniPT

[CVPR2024] The code of "UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory"

Srijith-rkr /KAUST-Whisper-Adapter

INTERSPEECH 23 - Refunction Whisper to recognize new tasks with adapters!

SALT-NLP /Adaptive-Compositional-Modules

Code for the ACL 2022 paper "Continual Sequence Generation with Adaptive Compositional Modules"

AuroraZengfh /ModalPrompt

[EMNLP'25 main] Official Implementation of ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt

Paranioar /SHERL

[ECCV2024] The code of "SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning"