vingstar's Stars
whitzard-ai/jade-db
"他山之石、可以攻玉":复旦白泽智能发布面向国内开源和国外商用大模型的Demo数据集JADE-DB
thu-coai/Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
Hannibal046/Awesome-LLM
Awesome-LLM: a curated list of Large Language Model
FudanMPL/Garnet
FudanMPL 2.0, a series of multi-party learning frameworks, with rich features, including secure and fast XGBoost, secure Fine-tuning for pre-trained models, and open source SecureML.
NVIDIA/NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
microsoft/presidio
Context aware, pluggable and customizable data protection and de-identification SDK for text and images
alibaba/Elastic-Federated-Learning-Solution
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
bytedance/byteps
A high performance and generic framework for distributed DNN training
microsoft/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
mli/paper-reading
深度学习经典、新论文逐段精读
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
meta-llama/llama
Inference code for Llama models
alibaba/EasyRec
A framework for large scale recommendation algorithms.
patcg-individual-drafts/ipa
Interoperable Private Attribution (IPA) - A Private Measurement Proposal
tiktok-privacy-innovation/PrivacyGo
Synergistic fusion of privacy-enhancing technologies for enhanced privacy protection.
microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
bytedance/Jeddak-DPSQL
DPSQL (Privacy Protection SQL Query Service) - This project is a microservice Middleware located between the database engine ( Hive , Clickhouse , etc.) and the application system. It provides transparent SQL query result desensitization capabilities.
secretflow/scql
SCQL (Secure Collaborative Query Language) is a system that allows multiple distrusting parties to run joint analysis without revealing their private data.
primihub/primihub
Privacy-Preserving Computing Platform 由密码学专家团队打造的开源隐私计算平台,支持多方安全计算、联邦学习、隐私求交、匿踪查询等。
bytedance/primus
alibaba/x-deeplearning
An industrial deep learning framework for high-dimension sparse data
tensorflow/recommenders
TensorFlow Recommenders is a library for building recommender system models using TensorFlow.
alibaba/FederatedScope
An easy-to-use federated learning platform
facebookresearch/fbpcs
FBPCS (Facebook Private Computation Solutions) leverages secure multi-party computation (MPC) to output aggregated data without making unencrypted, readable data available to the other party or any third parties. Facebook provides impression & opportunity data, and the advertiser provides conversion / outcome data.
google/ads-privacy
ciphermodelabs/ciphercore
User-friendly secure computation engine based on secure multi-party computation
Xtra-Computing/FedTree
A tree-based federated learning system (MLSys 2023)
secretflow/spu
SPU (Secure Processing Unit) aims to be a provable, measurable secure computation device, which provides computation ability while keeping your private data protected.
secretflow/secretflow
A unified framework for privacy-preserving data analysis and machine learning