Stars
Python bindings for FFmpeg - with complex filtering support
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
A framework to enable multimodal models to operate a computer.
Hydra is a framework for elegantly configuring complex applications
Manipulate audio with a simple and easy high level interface
Simple, Pythonic, text processing--Sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more.
⭐Github Ranking⭐ Github stars and forks ranking list. Github Top100 stars list of different languages. Automatically update daily. | Github仓库排名，每日自动更新
Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
A collection of libraries to optimise AI model performances
Fully local web research and report writing assistant
The Open edX LMS & Studio, powering education sites around the world!
Accessible large language models via k-bit quantization for PyTorch.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Utilities intended for use with Llama models.
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Pydoll is a library for automating chromium-based browsers without a WebDriver, offering realistic interactions.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.