You can deploy this model and start earning money today!

WangKaiLin/
PipeOwl

Name: PipeOwl
Availability: InStock

Views

No views yet

PipeOwl-1.0 (Geometric Embedding)

PipeOwl is a transformer-free geometric embedding package built on a static embedding field stored as NumPy arrays.

This repo provides:

L1_base_embeddings.npy: float32 (V, 1024) embedding table (unit-normalized)
L1_base_vocab.json: list of vocab strings aligned to embedding rows
delta_base_scalar.npy: float32 (V,) optional scalar bias field
minimal inference engine (engine.py) and usage script (quickstart.py)

Attribution

The base embedding vectors were generated using BGE (Apache-2.0) via inference (model outputs). This repository does not redistribute any original BGE model weights.

Quickstart

bash

pip install numpy
python quickstart.py

Or minimal usage:

python

from engine import PipeOwlEngine, PipeOwlConfig

engine = PipeOwlEngine(PipeOwlConfig())
q = engine.encode("雪鴞好可愛")
# use q for similarity / retrieval

Files

data/L1_base_embeddings.npy : embedding table (float32, V×1024)
data/L1_base_vocab.json : vocab aligned with rows
data/delta_base_scalar.npy : scalar bias (float32, V)
engine.py : minimal runtime
quickstart.py : example script

Notes

No safetensors / pytorch_model.bin is included because this model is distributed as a static NumPy embedding field.

Parameter Size

~165M embedding parameters (static matrix)

Intended Use

Semantic similarity
Lightweight retrieval
Geometric experimentation

Limitations

No contextual modeling
No token interaction modeling
Domain performance varies

Stress Test Results (Hard Retrieval Setting)

corpus size = 1200
eval size = 200
ood ratio = 0.28

Model	in-domain MRR@10	OOD MRR@10
MiniLM	0.019	0.026
BGE	0.026	0.009
PipeOwl	0.013	0.023

Note: This test uses a harder corpus and adversarial-style queries. Absolute scores are low due to difficulty scaling.

See full experimental notes here: https://hackmd.io/@galaxy4552/BkpUEnTwbl