Stars
ReadMe++: A Multi-domain Multilingual Dataset for Readability Assessment
🛏 An HTML to Markdown converter written in JavaScript
A script for converting .deb packages into Arch Linux packages, focused on accuracy
Перевод Руководства Таэ Кима на русский язык. Изначально сделан Андреем Воропаевым, развивается и пополняется.
A tiny (340 bytes) state manager for React/RN/Preact/Vue/Svelte with many atomic tree-shakable stores
Mechanistic Interpretability Visualizations using React
[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)
Robust recipes to align language models with human and AI preferences
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Rofi: A window switcher, application launcher and dmenu replacement
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
An autoregressive character-level language model for making more things
A Japanese tokenizer based on recurrent neural networks
Optical character recognition for Japanese text, with the main focus being Japanese manga
An audio server for yomichan that scrapes forvo for audio files
Anki add-on to run a local audio server for Yomichan.
A site with a broad array of tools for learning Japanese.
a structural diff that understands syntax 🟥🟩
A collection of Yomitan dictionaries created or modified by me.
Frequency dictionaries for yomitan based on the Corpus of Spontaneous Japanese and NINJAL Web Japanese Corpus datasets