Lists (3)
Sort Name ascending (A-Z)
Stars
一份面向实践者的 verl 框架使用教程。verl 是字节跳动开源的大语言模型强化学习训练框架,支持 PPO、GRPO 等多种算法,以及分布式训练、AgentRL 等场景。
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
这是我的强化学习笔记
An agentic skills framework & software development methodology that works.
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Dataflow-LoopAI is an intelligent system with self-optimization capabilities that automatically detects and evaluates generation deficiencies in LLMs within specific domains. Through dialog-based a…
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
中文翻译: https://github.com/forrestchang/andrej-karpathy-skills
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch
303 份 AI/LLM 中文讲义,支持在线阅读、PDF 下载和 LaTeX 源码查看 | Stanford CS336/CS224R/CS25 | Berkeley LLM Agents | Agent 工程实践
high performance coding with golang(Go 语言高性能编程,Go 语言陷阱,Gotchas,Traps)
An extension library of OpenTelemetry for Kitex
It's the extension for Kitex to load service governance config from Apollo (https://github.com/apolloconfig)
Tangseng search engine including full text search and vector search base on golang. 基于go语言的搜索引擎,信息检索系统
Algorithms and Data Structures implemented in Go for beginners, following best practices.
本项目是一个跨平台考勤系统,主要提供课前请假、教师审批、考勤申诉、督导点名、定位签到、指定督导等功能,分为学生端/督导端,和教师端。教师端实现考勤查询、教师审批和督导授权,采用VUE进行开发。
基于分布式架构,面向集群的福大助手服务端(2024 重构版),每日服务超 30,000 名师生
⭐ 【出版书籍】京东购买链接 https://item.jd.com/14531549.html 深入讲解内核网络、Kubernetes、ServiceMesh、容器等云原生相关技术。经历实践检验的“大规模分布式系统”开发指南。