Stars
SynchroTrap Algorithm Implementation
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
Implementation of all RL algorithms in a simpler way
DeepSeek Coder: Let the Code Write Itself
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈
Let your Claude able to think
All Algorithms implemented in Python
🧑🚀 全世界最好的LLM资料总结（视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
a collection of awesome autoregressive visual generation models
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
LangGPT: Empowering everyone to become a prompt expert!🚀 Structured Prompt，Language of GPT, 结构化提示词，结构化Prompt, Created by 「云中江树」
分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.
一个还算强大的Web思维导图。A relatively powerful web mind map.
「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。
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型，无需针对图片微调，即能生成高质量的个性风格化图片!
Integrate the DeepSeek API into popular softwares
RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information…
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.