SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.
- pytorch
- transformer
- pretrained-models
132,218 visible repositories in the index
1,969–1,992 of 3,447 · Most stars
SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.
UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image and UAV image segmentation.
Stable Diffusion web UI UX
A PyTorch toolkit for 2D Human Pose Estimation.
CrewMeld — Enterprise AI Digital Workforce Platform. Manage AI employees like real team members. Visual SOP orchestration, 13 LLM providers (including China-native models), 8+ messaging channels(WeCom/DingTalk/Feishu/Telegram), knowledge base with RAG, and full private deployment support. Built with Next.js, React, TypeScript & Bun.
Notes for Fastai Deep Learning Course
EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
A Python framework that emulates Grok Heavy functionality using intelligent multi-agent orchestration. Deploy 4 (or more) specialized AI agents in parallel to deliver comprehensive, multi-perspective analysis on any query.
🐙 The Go backend powering OCTO — an open workplace built for humans × AI agents. REST & WebSocket APIs, Lobster (AI agent) orchestration, and WuKongIM real-time messaging control plane.
Precompiled packages for AWS Lambda
We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundMind, a rule-based reinforcement learning (RL) algorithm tailored to endow audio language models (ALMs) with deep bimodal reasoning abilities.
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs
A library of concise, meaningful examples of Apex code for common use cases following best practices.
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
Support PyTorch model conversion with LiteRT.
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.
Workflow orchestration for AI agent swarms.
A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
A curated list of resources dedicated to reinforcement learning applied to cyber security.