Stars
OpenProject is the leading open source project management software.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Google Research
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
Datasets, Transforms and Models specific to Computer Vision
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Development repository for the Triton language and compiler
A library for efficient similarity search and clustering of dense vectors.
python parser for human readable dates
FAIR Chemistry's library of machine learning methods for chemistry
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
SchNetPack - Deep Neural Networks for Atomistic Systems
Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets
A minimalistic atomic Density Functional Theory (DFT) code
Hackable and optimized Transformers building blocks, supporting a composable construction.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
The continuation of the venerable JA2-Stracciatella project.
Tesseract Open Source OCR Engine (main repository)
Unsupervised text tokenizer for Neural Network-based text generation.
Open source annotation tool for machine learning practitioners.
💫 Industrial-strength Natural Language Processing (NLP) in Python
This repository contains implementations and illustrative code to accompany DeepMind publications
Open Source search based on OpenStreetMap data
Dedoc is a library (service) for automate documents parsing and bringing to a uniform format. It automatically extracts content, logical structure, tables, and meta information from textual electro…
Foundational Model for Speech Recognition Tasks
Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.