A simple evaluation of generative language models and safety classifiers.

Code for Bolmo: Byteifying the Next Generation of Language Models

LLMsploit a vulnerability scanner for Large Language Models.

PyMC port of Bayesian Bradley-Terry model for multi-algorithm multi-dataset comparison

[ACL'26 Findings] Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

[EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"

Project to generate POS tag dictionary for Ukrainian language

FastAPI Best Practices and Conventions we used at our startup

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

super fast cpp implementation of longest common subsequence/substring

Scikit-learn compatible library for molecular fingerprints and chemoinformatics

[ARCHIVED] A sophisticated data pipeline that creates meaningful collections of ENS names.

[ARCHIVED] Help your users discover ENS names they love with NameGraph.

ENSNode is the full-stack ENSv2 development platform.

Hackable and optimized Transformers building blocks, supporting a composable construction.

A library for language transfer methods and algorithms.

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Code and sources for the eval-UA-tion benchmark and paper

LLM papers I'm reading, mostly on inference and model compression

GPT-2 Metadata Pretraining Towards Instruction Finetuning for Ukrainian

Ukrainian ELECTRA model

розмічений руками морфо’, синт’, кореф’ корпус української мови

Natural language processing course thought at AGH University of Science and Technology

Ukrainian NLP

[ARCHIVED] Metadata for graphemes that may appear in ENS names

[ARCHIVED] Detailed inspection of labels in ENS names