Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
The definitive Web UI for local AI, with powerful features and easy setup.
⚡ A Fast, Extensible Progress Bar for Python and CLI
リアルタイムボイスチェンジャー Realtime Voice Changer
The interactive graphing library for Python ✨
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Companion code to my O'Reilly book "Flask Web Development", second edition.
Accessible large language models via k-bit quantization for PyTorch.
Convolutional Neural Network for Text Classification in Tensorflow
Google Drive Public File Downloader when Curl/Wget Fails
[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving
A synthetic data generator for text recognition
Image Deblurring using Generative Adversarial Networks
Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch
A system for assigning and grading notebooks
Composable GAN framework with api and user interface
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
Efficient Counter that uses a limited (bounded) amount of memory regardless of data size.
A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.
Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes
Pure-Python Japanese character interconverter for Hiragana, Katakana, Hankaku, and Zenkaku
Tutorial to train fastText with Japanese corpus
This is the official implementation of TrivialAugment and a mini-library for the application of multiple image augmentation strategies including RandAugment and TrivialAugment.