Open source. Open possibilities.

Official code repository for 'Build a Large Language Model (From Scratch)': step-by-step PyTorch implementation of GPT-like models, covering pretraining and finetuning with notebooks and exercises.

Collection of simple PyTorch implementations of neural networks and deep learning papers with documented side-by-side explanations, covering transformers, GANs, diffusion models, RL, optimizers, and more.

Drowse is a local workbench for mechanistic interpretability of large language models, offering a dashboard, Python API, and OpenAI/Ollama-compatible server for activation steering, concept probes, manifolds, SAEs, and Jacobian lenses.

DocsGPT is an open-source AI platform for building intelligent agents and assistants, featuring document analysis, multi-model support, and enterprise search capabilities.

Free, open-source AI engineering curriculum from first principles: 523 lessons in 20 phases (~342 hours), with math-to-production coverage in Python, TypeScript, Rust, and Julia. Every lesson ships a reusable prompt, skill, agent, or MCP server; includes an installable AI tutor and Claude certification prep.

A curated collection of 107 foundational generative AI research papers with comprehensive summaries, learning roadmaps, glossaries, and decision guides—making cutting-edge AI research accessible to everyone.

An all-in-one AI framework for semantic search, LLM orchestration, and language model workflows.

A practical, from-scratch guide to training LLMs using PyTorch, covering data preparation, building a Transformer, pretraining, and post-training with SFT, DPO, PPO, and GRPO.

Xinference is a unified inference library for serving language, speech, and multimodal models. It provides OpenAI-compatible RESTful API, heterogeneous GPU/CPU utilization, distributed deployment, and integrates with LangChain, LlamaIndex, Dify, and Chatbox.

LlamaFactory is a Python framework for efficient fine-tuning of 100+ large language and multimodal models, offering zero-code CLI, a Gradio Web UI, LoRA/QLoRA, and multiple training algorithms.

A free 21-lesson Microsoft course for beginners to build generative AI applications, covering LLMs, prompt engineering, RAG, agents, fine-tuning, and more, with Python/TypeScript examples.

SANA is NVIDIA's open-source family of efficient diffusion models for high-resolution image and video generation, with training and inference code, linear attention, DC-AE compression and 4-bit deployment.