🚀 Efficient implementations for emerging model architectures
- large-language-models
- machine-learning-systems
- natural-language-processing
- sequence-modeling
132,241 visible repositories in the index
289–312 of 2,770 · Most stars
🚀 Efficient implementations for emerging model architectures
👷 Build images with images
Personalized Unattended Answer Files that helps automatically debloat and customize Windows 10 & 11 during the installation process.
:alarm_clock: AI conference deadline countdowns
Alphabetical list of free/public domain datasets with text data for use in Natural Language Processing (NLP)
Effort free video editing!
AI audio watermark removal & forensic anti-attribution toolkit. Neutralizes Suno, Udio, and neural fingerprints with ISO 226 perceptual masking.
The open source mesh processing system
High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale
A cross-language remote procedure call(RPC) framework for rapid development of high performance distributed services.
⚡️ OpenAI PHP is a supercharged community-maintained PHP API client that allows you to interact with OpenAI API.
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
A Unified Toolkit for Deep Learning Based Document Image Analysis
High-Performance Serverless event and data processing platform
Imaging is a simple image processing package for Go
😎 Finding duplicate images made easy!
A generic post-processing injector for games and video software.
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Blurry is an easy blur library for Android
Convert PDF to HTML without losing text or format.
An implementation of Shazam's song recognition algorithm.
In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.
qpdf: A content-preserving PDF document transformer
Blackfriday: a markdown processor for Go