Principal Scientist at Keenable AI
rulm. Language modeling and instruction tuning for Russian
466rupo. Библиотека для анализа и генерации стихов на русском языке
179summarus. Models for automatic abstractive summarization
172rnnmorph. Morphological analyzer for Russian and English languages based on neural networks and dictionary-lookup systems.
159ping_pong_bench. A benchmark for role-playing language models
120tgcontest. Telegram Data Clustering contest solution by Mindful Squirrel
95academia_mcp. Academia MCP server: Tools for automatic scientific research
90saiga_bot. Telegram bot for different language models. Supports system prompts and images
67saiga. Training and data processing code for Saiga
56holosophos. Tools and agents for automated research.
55UNMT. Code inspired by Unsupervised Machine Translation Using Monolingual Corpora Only
50PoetryCorpus. Поэтический корпус русского языка
44codearkt. Implementation of the CodeAct agentic framework with Docker containers for security, MCP servers for tool integrations, and multi-agent support.
40gazeta. Gazeta: Dataset for automatic summarization of Russian news / Газета: набор данных для автоматического реферирования на русском языке
38tg_chat_search. Python
21memetron3000. LLM-based meme generator with templates
14HeadlineCause. A dataset of news headlines for detecting causalities
14russ. Package for word stress detection
11TaleStudio. Fork of RecurrentGPT with modifications
10rudetox. Python
7purano. News annotation and clustering
7Algorithms. Algorithms on C++ and C
7IlyaGusev. HTML
6nghack. Решение НГ Hack от Mindful Squirrel
6MIPT_Algo_Seminars. Материалы для семинаров по курсу "Алгоритмы и структуры данных" ФПМИ МФТИ
5mle_kit_mcp. MLE kit MCP server: Tools for working with files and code locally and with a remote GPU
4aika. Amateur level C++ chess engine with web GUI on top of lc0 board representation
3smolagents. 🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
3quest. Quantitative evalUation of modErn LLM Sampling Techniques
3unsloth-zoo. Utils for Unsloth
3translate_api. Python
2SentiRuEval-2016. Jupyter Notebook
2alpaca-lora. Instruct-tune LLaMA on consumer hardware
2nlp-homework. Задание по курсу NLP
2telegram-news. Python package for automatically fetching and pushing news by Telegram.
1babel-submitions. Jupyter Notebook
1remotion. Эксперименты по аспектному анализу тональности
1worker-vllm. The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
1dialogue-latex. LaTeX Template for the Dialogue Conference.
1docmost. Docmost is an open-source collaborative wiki and documentation software. It is an open-source alternative to Confluence and Notion.
1trl. Train transformer language models with reinforcement learning.
1Plotter. Graph plotter, MathML and TeX support
1