🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

Composable building blocks to build Llama Apps

DeepSeek LLM: Let there be answers

Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )

Privacy-Preserving Prompt Tuning for Large Language Model

A course on aligning smol models.

A library for running membership inference attacks against ML models

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

Github Pages template for personal, portfolio-based websites; forked from mmistakes/minimal-mistakes

PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker/Zotero

PyTorch Implementation of Learning to Prompt (L2P) for Continual Learning @ CVPR22

This is the source code of "Self-Paced Continual Learning with Adaptive Curriculum and Memory Replay".

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

This is the source code of "Self-Paced Continual Learning with Adaptive Curriculum and Memory Replay". (2024 IEEE BigData)

This is the source code of "OL4TeX: Adaptive Online Learning for Text Classification under Distribution Shifts".

Feature Translation for Exemplar-Free Class-Incremental Learning

Official Implementation of the ECCV 2022 Paper "Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer"

(CVPR 2022) Energy-based Latent Aligner for Incremental Learning

Acceptance rates for the major AI conferences

Pretrained models on CIFAR10/100 in PyTorch

Official Repository for the ICML 2023 paper "BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning"

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

Dynamic Token Expansion with Continual Transformers, accepted at CVPR 2022