torch

Stable Diffusion web UI

A generative speech model for daily dialogue.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Setup and customize deep learning environment in seconds.

Superduper: End-to-end framework for building custom AI applications and agents.

Probabilistic time series modeling in Python

Solve puzzles. Improve your pytorch.

A comprehensive list of Deep Learning / Artificial Intelligence and Machine Learning tutorials - rapidly expanding into areas of AI/Deep Learning / Machine Vision / NLP and industry specific areas such as Climate / Energy, Automotives, Retail, Pharma, Medicine, Healthcare, Policy, Ethics and more.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

View model summaries in PyTorch!

Fast stable diffusion on CPU and AI PC

C++ Implementation of PyTorch Tutorials for Everyone

🤖 A Python library for learning and evaluating knowledge graph embeddings

Collaboration with wangxupeng(https://github.com/wangxupeng)

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

GemPy is an open-source, Python-based 3-D structural geological modeling software, which allows the implicit (i.e. automatic) creation of complex geological models from interface and orientation data. It also offers support for stochastic modeling to address parameter and model uncertainties.

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

Jetson Nano with Ubuntu 20.04 image

深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)

Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

R Interface to Torch

A DIY mouth tracking method for VR

Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)

gradio WebUI for AdvancedLivePortrait

Akarin is a powerful server software from the 'new dimension'