SUGIYAMA Yoshio's starred repositories
nerd-fonts
Iconic font aggregator, collection, & patcher. 3,600+ icons, 50+ patched fonts: Hack, Source Code Pro, more. Glyph collections: Font Awesome, Material Design Icons, Octicons, & more
llama_index
LlamaIndex is a data framework for your LLM applications
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
PokemonRedExperiments
Playing Pokemon Red with Reinforcement Learning
self-instruct
Aligning pretrained language models with instruction data generated by themselves.
ChatGPT.nvim
ChatGPT Neovim Plugin: Effortless Natural Language Generation with OpenAI's ChatGPT API
LLMDataHub
A quick guide (especially) for trending instruction finetuning datasets
DeepSpeed-MII
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
sqlite-vss
A SQLite extension for efficient vector search, based on Faiss!
AlpacaDataCleaned
Alpaca dataset from Stanford, cleaned and curated
SlideshowAnimations
A collection of ideas for slideshow animations.
vim-quickhl
quickly highlight <cword> or visually selected word
symbol-usage.nvim
Display references, definitions and implementations of document symbols
auto-indent.nvim
Auto indent like VSCode when cursor at the first column and press <TAB> key
simple-simcse-ja
Exploring Japanese SimCSE
nvim-lspimport
Automatically resolves imports for undefined terms in neovim.
profiler-workshop
Example code for profiler workshop
RAG-with-MLDE
LLM RAG System with MLDE