🤗 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

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Fully open reproduction of DeepSeek-R1

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

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

verl: Volcano Engine Reinforcement Learning for LLMs

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Nano vLLM

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

Object detection, 3D detection, and pose estimation using center point detection:

Google AI 2018 BERT pytorch implementation

Demo of a customer service use case implemented with the OpenAI Agents SDK

slime is an LLM post-training framework for RL Scaling.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

A live stream development of RL tunning for LLM agents

Simple RL training for reasoning

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Official Repository of Absolute Zero Reasoner

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

The official implementation of Self-Play Fine-Tuning (SPIN)

AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.