konoha
🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.
- 265
- Python
- MIT
- 7 d ago
himkt
Built from himkt's public GitHub profile, Tokyo, Japan. Not on Take My Repo yet, so there are no posts or updates here.
🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.
📝 A list of pre-trained BERT models for Japanese with word/subword tokenization + vocabulary construction algorithm information
🛰️ Coding Agent Fleet (cafleet) is a coding agent orchestrator for multi-agents collaboration across coding agent providers
🌈 Implementation of Neural Network based Named Entity Recognizer (Lample+, 2016) using Chainer.
🪄 Dotfiles, claude code configs, and system settings for macOS & Linux, which makes everyday software development fun!
⚡️ AllenNLP plugin for adding subcommands to use Optuna, making hyperparameter optimization easy
👀 Interest: Organizing papers+materials which you are interested in. Serverless application powered by GitHub pages + Google Spreadsheet.
📚 MCP client for jumping to definitions using LSP server for an arbitrary language
🔯 My claude code setting using agent teams, which makes everyday software development effective!
🦀 Handmade data structure and algorithm implementation for programming contest, written in Rust
🔧 Visual Studio Code extension for AtCoder, especially for Rustacean, based on cargo-atcoder