Stars
An agentic skills framework & software development methodology that works.
0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Supercharge Your LLM Application Evaluations 🚀
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agen…
A framework for few-shot evaluation of language models.
Fully open reproduction of DeepSeek-R1
Minimal reproduction of DeepSeek R1-Zero
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。
Video+code lecture on building nanoGPT from scratch
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
LlamaIndex is the leading document agent and OCR platform
A high-throughput and memory-efficient inference and serving engine for LLMs