Stars
Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"
Ongoing research training transformer models at scale
Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Dapr, Rancher Desktop, and Kuberne…
An open protocol enabling communication and interoperability between opaque agentic applications.
跨平台 Python 异步聊天机器人框架 / Asynchronous multi-platform chatbot framework written in Python
Cross-platform, customizable multimedia/video processing framework. With strong GPU acceleration, heterogeneous design, multi-language support, easy to use, multi-framework compatible and high perf…
✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨ 平台支持 QQ、QQ频道、Telegram、微信、企微、飞书、钉钉 | 知识库、MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify 等。 WebUI。
Start building LLM-empowered multi-agent applications in an easier way.
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
Recipes to train reward model for RLHF.
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Learning Large Language Model (LLM）(大语言模型学习)
"AI-Researcher: Autonomous Scientific Innovation"
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Async Agent RL)
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
No fortress, purely open ground. OpenManus is Coming.
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Code for the paper "Language Models are Unsupervised Multitask Learners"