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

Unsloth Studio is a web UI for training and running open models like Qwen3.5, Gemma 4, DeepSeek, gpt-oss locally.

Inference code for Llama models

The world's simplest facial recognition api for Python and the command line

Ultralytics YOLO 🚀

The best ChatGPT that $100 can buy.

Run frontier AI locally.

🎨 Diagram as Code for prototyping cloud system architectures

TensorFlow code and pre-trained models for BERT

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

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Python logging made (stupidly) simple

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Nano vLLM

Hierarchical Reasoning Model Official Release

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

Twitter for Python!

Ollama Python library

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Speech recognition module for Python, supporting several engines and APIs, online and offline.

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

Example models using DeepSpeed

Google AI 2018 BERT pytorch implementation

Efficient Triton Kernels for LLM Training

Robust recipes to align language models with human and AI preferences

Python client library for Google Maps API Web Services