🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A high-throughput and memory-efficient inference and serving engine for LLMs

Ongoing research training transformer models at scale

翻墙-科学上网、自由上网、免费科学上网、免费翻墙、fanqiang、油管youtube/视频下载、软件、VPN、一键翻墙浏览器，vps一键搭建翻墙服务器脚本/教程，免费shadowsocks/ss/ssr/v2ray/goflyway账号/节点，翻墙梯子，电脑、手机、iOS、安卓、windows、Mac、Linux、路由器翻墙、科学上网、youtube视频下载、youtube油管镜像/免翻墙…

Curated list of datasets and tools for post-training.

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

🦜🔗 The platform for reliable agents.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Lightweight coding agent that runs in your terminal

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Build resilient language agents as graphs.

An open-source AI agent that brings the power of Gemini directly into your terminal.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

DSPy: The framework for programming—not prompting—language models

The official Python SDK for Model Context Protocol servers and clients

A lightweight, powerful framework for multi-agent workflows

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

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

PyTorch native post-training library

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Production-ready platform for agentic workflow development.

verl: Volcano Engine Reinforcement Learning for LLMs

UltraRAG 2.0: Less Code, Lower Barrier, Faster Deployment! MCP-based low-code RAG framework, enabling researchers to build complex pipelines to creative innovation.

UltraRAG 2.2