Experiments in Interactive Learning

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

A globally distributed container orchestrator

Utils for Unsloth

A library for mechanistic interpretability of GPT-style language models

Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers

Streaming and Finetuning code for CSM

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.

The official implementation of Recurrent Diffusion for Large-Scale Parameter Generation.

Robust, lightweight, configurable python-poetry Docker images for any use case.

Core utilities for creating AI agent tools

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

A codebase for "Language Models can Solve Computer Tasks"

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

Python project/package root path detection.

Docs for RasgoQL

Define Kubernetes native apps and abstractions using object-oriented programming

Retype is an ✨ ultra-high-performance✨ static site generator that builds a website based on simple text files.