XMap is a fast network scanner designed for performing Internet-wide IPv6 & IPv4 network research scanning.

一款轻量级开源车载领域通信中间件，支持HTTP、MQTT、SOME/IP、SOME/IP-SD等协议以及多种IPC方式

Official Implementation of ICML'23 "Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting".

2023年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

C++高性能分布式服务器框架,webserver,websocket server,自定义tcp_server（包含日志模块，配置模块，线程模块，协程模块，协程调度模块，io协程调度模块，hook模块，socket模块，bytearray序列化，http模块，TcpServer模块，Websocket模块，Https模块等, Smtp邮件模块, MySQL, SQLite3, ORM,Red…

Achieve a tiny STL in C++11

MIT 6.824 distributed system C++Version

Autoencoder based intrusion detection system trained and tested with the CICIDS2017 data set.

A Novel Statistical Analysis and Autoencoder Driven Intelligent Intrusion Detection Approach

Build your own Custom RAG Chatbot using Gradio, Langchain and Llama2

A simple Langchain RAG application.

Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.

MobileBERT and DistilBERT for extractive summarization

LLAMA specialized on finance

Scripts for fine-tuning Llama2 via SFT and DPO.

A clean implementation of direct preference optimization (DPO) to train the LLaMA 2 model to align with human preferences.

A minimum example of aligning language models with RLHF similar to ChatGPT

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various c…

MVP for a Retail Investment Advisor Powered by LLMs - CalHacks 2023 Hackathon

In this project, I explored how local LLMs can be used to label data and support analyses. Specifically, I used Llama2 model to automatically categorise my bank transaction data.

[TOG 2024]StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

KDSS is the framework for knowledge distillation from LLMs

Robust recipes to align language models with human and AI preferences

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

Federated Learning for Intrusion Detection System using the Flower framework and UNSW_NB15 dataset.

This project focuses on detecting IoT botnets using advanced techniques like autoencoders, LSTM-CNN, and DNN. Enhancing security and preventing botnet attacks in the Internet of Things.

IoT Inspector: capturing and analyzing your smart home network traffic

PyTorch & Keras implementation for BraTs (Brain Tumor Segmentation)

UNet for brain tumor segmentation