Kazuki Fujii's Projects
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
Japanese Simple-SimCSE
Home of StarCoder: fine-tuning & inference!
Sudachi in Rust 🦀 and new generation of SudachiPy
『Webブラウザセキュリティ ― Webアプリケーションの安全性を支える仕組みを整理する』サンプルコード
2021-3Q 論理回路理論 (Tokyo Tech)
2022-1Q システムプログラミング (Tokyo Tech)
Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
システム設計演習 Tokyo Institute of Technology
Tokyo Institute of Technology (B3)
東工大 学部3年次 研究プロジェクト(小野研)
Tokyo Institute of Technology Workshop on System Design
for scraping tokyo tech ocw
A native PyTorch Library for large model training
ECS task event/log tracer CLI
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
環境構築方法の詳細は以下のLinkから
traP なろう講習会
ABCI 大規模言語モデル構築支援にてwandbのジョブを監視するためのツール