「大規模言語モデル入門」（2023）と「大規模言語モデル入門Ⅱ〜生成型LLMの実装と評価」（2024）のGitHubリポジトリ

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Codes and materials for the "Introduction to finite element using FreeFEM" series.

Clean card Hugo theme for blog, created by using tailwindcss

Build resilient language agents as graphs.

Hands on lab for Neo4j and Amazon Bedrock

zennの記事にて紹介した, langchainを用いた4種類のチェーンの実装とテストを行うためのリポジトリです!

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Jupyter notebooks that support my graph data science blog posts at https://bratanic-tomaz.medium.com/

Python Implementation of EmbedRank

日本語LLMまとめ - Overview of Japanese LLMs

Typescript Minimal Starter Boilerplate - Webpack 5 🚀, Babel 7, UMD, Unit Testing

Truly independent web browser

Lightweight & optimized Multi-Arch Docker Images (x86_64/arm/arm64) for PHP-FPM (PHP 8.1, 8.2, 8.3) with essential extensions on top of latest Alpine Linux. 🐘

VAE for color images

Docker-image contains built PHP 8 for docker-compose-php project

ESC-50: Dataset for Environmental Sound Classification

U-Net convolutional network to remove Gibbs noise in 1D time signal

Robust Speech Recognition via Large-Scale Weak Supervision

Noisy-ArcMix: Additive Noisy Angular Margin Loss Combined With Mixup for Anomalous Sound Detection

Implementation of the Wave-U-Net for audio source separation

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".