Measuring Massive Multitask Language Understanding | ICLR 2021
- muti-task
- transfer-learning
- gpt-3
- few-shot-learning
132,241 visible repositories in the index
121–144 of 309 · Most stars
Measuring Massive Multitask Language Understanding | ICLR 2021
Official Pytorch implementation of the preprint paper "Stylized Neural Painting", in CVPR 2021.
resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor
High Quality Monocular Depth Estimation via Transfer Learning
.NET Framework for Backgrounding & Device Hardware Services (iOS, MacOS, tvOS, Android, Windows, Linxux, & Web)
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
An implementation of "A Neural Algorithm of Artistic Style" by L. Gatys, A. Ecker, and M. Bethge. http://arxiv.org/abs/1508.06576.
✂️ Automated high-quality background removal framework for an image using neural networks. ✂️
A self-hostable complete file-sharing solution that focuses on reliability, security and ease of use.
simplest & fastest way to transfer files between computers via WireGuard
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
trzsz ( trz / tsz ) is a simple file transfer tool, similar to lrzsz ( rz / sz ), but compatible with tmux.
Code for TKDE paper "Self-supervised learning on graphs: Contrastive, generative, or predictive"
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel® XPU (CUDA also supported).
The source code of 'Visual Attribute Transfer through Deep Image Analogy'.
Demo of in-browser Fast Neural Style Transfer with deeplearn.js library
Collection of awesome test-time (domain/batch/instance) adaptation methods
A lightweight, cloud-native data transfer agent and aggregator
A comprehensive list of awesome contrastive self-supervised learning papers.
sophisticated command line file transfer program (ftp, http, sftp, fish, torrent)
Now upgraded to .NET 10, this project is a super-fast, completely headless API powered by Clean Architecture, CQRS, and MediatR. It includes an ASP.NET Core Razor Pages implementation for inventory order management, combined with Vue.js for a dynamic, responsive UI. Powerful WMS solution. Demo (username:[email protected] / pwd:123456)
Official implementations for paper: Zero-shot Image Editing with Reference Imitation