An Open Source Machine Learning Framework for Everyone

Making large AI models cheaper, faster and more accessible

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

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent & VSCode Agent (And other Open Sourced) System Prompts, Tools & AI Models.

Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

s1: Simple test-time scaling

User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Tools for merging pretrained large language models.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

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…

🚀🚀 「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!

CUDA 算子手撕与面试指南

Large Reasoning Models

Code and documentation to train Stanford's Alpaca models, and generate the data.