Silero Stress — pre-trained enterprise-grade automated stress and homograph disambiguation for the Russian language

Ultralytics YOLO 🚀

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…

Chu-Lui-Edmonds decoding extracted from TurboParser

Chu-Liu-Edmonds maximum spanning algorithm from TurboParser for use within Python

A multilingual dependency parser based on linear programming relaxations.

Fallout 2 for modern operating systems

Isometric action game engine

aiopg is a library for accessing a PostgreSQL database from the asyncio

A fast PostgreSQL Database Client Library for Python/asyncio.

Part-of-Speech Tagger for Russian language

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

Open Source search based on OpenStreetMap data

Foundational Model for Speech Recognition Tasks

Morphological analyzer / inflection engine for Russian and Ukrainian languages. Fork of https://github.com/pymorphy2/pymorphy2

Morphological analyzer / inflection engine for Russian and Ukrainian languages.

DAFSA-based dictionary-like read-only objects for Python. Based on `dawgdic` C++ library. Fork of https://github.com/pytries/DAWG

🧑‍🚀 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.

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.

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

ExplainitAll — это библиотека для интерпретируемого ИИ, предназначенная для интерпретации генеративных моделей ( GPT-like), и векторизаторов, например, Sbert.

Metric learning and retrieval pipelines, models and zoo.

Mamba SSM architecture

"Руформеры" - список популярных базовых моделей на основе трансформеров для решения задач по автоматической обработке русского языка

A fast inference library for running LLMs locally on modern consumer-class GPUs

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Official inference library for Mistral models

OpenChat: Advancing Open-source Language Models with Imperfect Data

OpenProject is the leading open source project management software.

OpenMMLab Text Detection, Recognition and Understanding Toolbox