HuggingFace conversion and training library for Megatron-based models

Bridge Megatron-Core to Hugging Face/Reinforcement Learning

AgentScope: Agent-Oriented Programming for Building LLM Applications

The best ChatGPT that $100 can buy.

Fully open data curation for reasoning models

Build AI Agents, Visually

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Memory Augmented Neural Networks (Pytorch)

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates. - Professor Yu Liu

Concatenate a directory full of files into a single prompt for use with LLMs

📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

Data validation using Python type hints

🧠 Curated collection of system prompts for top AI tools. Perfect for AI agent builders and prompt engineers. Incuding: ChatGPT, Claude, Perplexity, Manus, Claude-Code, Loveable, v0, Grok, same new,…

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

The absolute trainer to light up AI agents.

GPT powered sorting using structured output

A course on aligning smol models.

[TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

[ICML 2025] Official code of "DAMA: Data- and Model-aware Alignment of Multi-modal LLMs"

Translate PDF, EPub, webpage, metadata, annotations, notes to the target language. Support 20+ translate services.

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

The official code of ARPO & AEPO

Train transformer language models with reinforcement learning.

A curated list of reinforcement learning with human feedback resources (continually updated)