You can deploy this model and start earning money today!

WangKaiLin/
PipeOwl-1.11-bilingual

Name: PipeOwl-1.11-bilingual
Availability: InStock

Views

No views yet

PipeOwl-1.11-bilingual (Geometric Embedding)

A transformer-free semantic retrieval engine.

Features:

O(n) over vocabulary.
No attention.
No transformer weights.

Architecture

Static embedding table (V × D)
Aligned vocabulary index
Linear scoring
Pluggable decoder stage

Model Specs

item	value
token size	524190
embedding dim	256
storage format	safetensors (FP16)
data size	~267 MB
languages	bilingual
startup time	~478 ms
query latency	~25-34 ms

Quickstart

bash

git clone https://huggingface.co/WangKaiLin/PipeOwl-1.11-bilingual
cd PipeOwl-1.11-bilingual

pip install numpy safetensors

python quickstart.py

Example:

Example semantic retrieval results:

bash

請輸入句子： 確實

Top-K Tokens:
000 | 確實
877 | 的確
839 | 确实
772 | 的确
757 | 事實上

請輸入句子： 今天好想睡覺

Top-K Tokens:
761 | 今天
747 | 今天的
694 | 睡觉
693 | 刚才
685 | 现在

請輸入句子： i want to sleep

Top-K Tokens:
719 | sleep
663 | schlafen
638 | want
616 | sleeping
616 | tidur

請輸入句子： 哈囉你好阿

Top-K Tokens:
825 | 哈囉
818 | 你好
769 | 嘿
759 | 嗨
750 | Kaixo

Repository Structure

bash

PipeOwl-1.11-bilingual/
 ├ README.md
 ├ config.json
 ├ LICENSE
 ├ quickstart.py
 ├ engine.py
 ├ tokenizer.json
 └ pipeowl.safetensors

🔌 Optional: RAG Integration

PipeOwl can be combined with the RAG pipeline from PipeOwl-1.10.2-tw-wiki-rag.

You can reuse the wiki retrieval layer and directly plug it on top of PipeOwl-1.11 embeddings.

PipeOwl provides fast semantic token retrieval

RAG layer provides document-level grounding

Integration Approach

Replace the embedding backend with PipeOwl-1.11

Keep the existing:

wiki index
entity layer
merge retriever

Use PipeOwl output tokens as query expansion

Result

⚡ Faster retrieval (edge-ready)
📚 Same wiki grounding capability
🧠 Better semantic recall with bilingual support

LICENSE

MIT