- Shanghai, China
- goncha.github.com
Stars
Neural Networks: Zero to Hero
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >70% on SWE-bench verified!
Yet another unofficial speedtest.net client cli interface
CLI tool to see redis memory usage by keys in hierarchical way. Think of disk inventory but for redis.
A high-throughput and memory-efficient inference and serving engine for LLMs
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Use your locally running AI models to assist you in your web browsing
「海外工具网站」已经是我人生主要事业了,很庆幸还来得及,感谢这个伟大的 AI 时代。
Code for the AAAI'23 paper "Yet Another Traffic Classifier: A Masked Autoencoder Based Traffic Transformer with Multi-Level Flow Representation"
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Linux tool for sniffing smartcard communication between card and reader using season interface.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Jupyter notebooks for the Natural Language Processing with Transformers book
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Vulnerability scanner written in Go which uses the data provided by https://osv.dev
一款长亭自研的完善的安全评估工具,支持常见 web 安全问题扫描和自定义 poc | 使用之前务必先阅读文档
A simple, lightweight PowerShell script to remove pre-installed apps, disable telemetry, as well as perform various other changes to customize, declutter and improve your Windows experience. Win11D…
Deep Reinforcement Learning: Zero to Hero!
tiny, portable SOCKS5 server with very moderate resource usage