item	value
vocab size	26155
embedding dim	768
storage format	safetensors (FP16)
model size	~38.7 MB
languages	Japanese
startup time	<1s
query latency	~3-4 ms (CPU, full vocabulary scan)

Attribution

DATA_SOURCES.md

Quickstart

bash

git clone https://huggingface.co/WangKaiLin/PipeOwl-1.5-jp
cd PipeOwl-1.5-jp

pip install numpy safetensors

python quickstart.py

Example:

Example semantic retrieval results:

bash

Please enter words： 日

Top-K Tokens:
974 | 日
794 | 日の
789 | 翌日
777 | 週
775 | 週間

Please enter words： 行

Top-K Tokens:
961 | 行
794 | 行こ
787 | 執り行
787 | 入
784 | 起

Please enter words： 東京

Top-K Tokens:
979 | 東京
872 | 大阪
868 | 名古屋
849 | 横浜
848 | 目黒

Benchmark (CPU)

Environment:

Vocab size: 26,155
Embedding dimension: 768
Hardware: CPU

Average query latency:

PipeOwl: 0.0036 sec
BM25: 0.0421 sec
Embedding: 0.0283 sec
FAISS Flat: 0.0324 sec
FAISS HNSW: 0.0230 sec

Comparison	Speedup
vs BM25	11.7× faster
vs Embedding	7.9× faster
vs FAISS Flat	9.0× faster
vs FAISS HNSW	6.4× faster

PipeOwl shows 6–12× lower latency compared with common retrieval baselines in this setup.

repo: https://huggingface.co/datasets/WangKaiLin/pipeowl-1.5-jp-benchmark

Repository Structure

bash

pipeowl-1.5-jp/
 ├ README.md
 ├ config.json
 ├ DATA_SOURCES.md 
 ├ LICENSE
 ├ quickstart.py
 ├ engine.py
 ├ vocabulary.json
 └ pipeowl_fp16.safetensors

LICENSE

MIT