Kazuhiro Serizawa's starred repositories
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
ydata-profiling
1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
alpaca.cpp
Locally run an Instruction-Tuned Chat-Style LLM
quicktemplate
Fast, powerful, yet easy to use template engine for Go. Optimized for speed, zero memory allocations in hot paths. Up to 20x faster than html/template
webdataset
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
dataloader
Implementation of Facebook's DataLoader in Golang
machine-learning-round-table
Gather around the table, and have a discussion to catch up the latest trend of machine learning 🤖
actions-timeline
An Action shows timeline of a workflow in a run summary.
game-programmer-book-build
ゲームプログラマーになる前に覚えておきたい技術 近代化プロジェクト
alpaca-lora-create-news-title
Alpaca-LoRAをlivedoorニュースコーパスでFineTuningさせるサンプルコード
gpt-voice-chat
A real voice chat with ChatGPT AI
NicoApiClient
ニコニコ動画 『スナップショット検索API v2』 仕様をなるべく意識せずに利用できる Python クライアント