- Beijing,China
Stars
Making large AI models cheaper, faster and more accessible
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
Stable Diffusion web UI
An open-source NLP research library, built on PyTorch.
A virtual file system adapter for Azure Blob storage
Visualizer for neural network, deep learning and machine learning models
microsoft / Megatron-DeepSpeed
Forked from NVIDIA/Megatron-LMOngoing research training transformer language models at scale, including: BERT & GPT-2
Unsupervised text tokenizer for Neural Network-based text generation.
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
Code for the ACL 2022 paper "Contextual Representation Learning beyond Masked Language Modeling"
A V2Ray client for Android, support Xray core and v2fly core
Example models using DeepSpeed
程序员延寿指南 | A programmer's guide to live longer
Efficient, check-pointed data loading for deep learning with massive data sets.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
雀魂Plus——雀魂麻将Majsoul专用浏览器,提供了一些专有特性
🔍🀄️ Review mahjong game log with mjai-compatible mahjong AI.
Toolkit for creating, sharing and using natural language prompts.
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
⚓ 我的游戏程序员生涯的读书笔记合辑。你可以把它看作一个加强版的Blog。涉及图形学、实时渲染、编程实践、GPU编程、设计模式、软件工程等内容。Keep Reading , Keep Writing , Keep Coding.
A benchmark for the task of translation suggestion
Prefix-Tuning: Optimizing Continuous Prompts for Generation
A modern, high customizable, responsive Jekyll theme for documentation with built-in search.