hyper-models

A model zoo for non-Euclidean embedding models
Hyperbolic · Spherical · Product Manifolds

---

Why?

• Standardized access to non-Euclidean embedding models
• Torch-free runtime via ONNX (models published to Hugging Face Hub)
• Simple API — load() and encode_images()

Installation

pip install hyper-models

Usage

import hyper_models
from PIL import Image

# List available models
hyper_models.list_models()
# ['hycoclip-vit-s', 'hycoclip-vit-b', 'meru-vit-s', 'meru-vit-b']

# Load model (auto-downloads from Hugging Face Hub)
model = hyper_models.load("hycoclip-vit-s")
model.geometry  # 'hyperboloid'
model.dim       # 513

# Encode PIL images
images = [Image.open("image.jpg")]
embeddings = model.encode_images(images)  # (1, 513) ndarray

# Get model info
info = hyper_models.get_model_info("hycoclip-vit-s")
info.hub_id     # 'mnm-matin/hyperbolic-clip'
info.license    # 'CC-BY-NC'

# Low-level: preprocess images yourself
batch = hyper_models.preprocess_images(images)  # (B, 3, 224, 224)
embeddings = model.encode(batch)

Models

Hyperbolic

Model	Available	Paper	Code
hycoclip-vit-s		ICLR 2025	PalAvik/hycoclip
hycoclip-vit-b		ICLR 2025	PalAvik/hycoclip
meru-vit-s		ICML 2023	facebookresearch/meru
meru-vit-b		ICML 2023	facebookresearch/meru
hyp-vit	—	CVPR 2022	htdt/hyp_metric
hie	—	CVPR 2020	leymir/hyperbolic-image-embeddings
hcnn	—	ICLR 2024	kschwethelm/HyperbolicCV

Hyperspherical

Model	Available	Paper	Code
megadescriptor		WACV 2024	WildlifeDatasets/wildlife-datasets
sphereface	—	CVPR 2017	wy1iu/sphereface
arcface	—	CVPR 2019	deepinsight/insightface

Product Manifolds

Model	Available	Paper	Code
hyperbolics	—	ICLR 2019	HazyResearch/hyperbolics

Export Tooling

This repo also contains tooling to export PyTorch models to ONNX:

cd export/hycoclip
uv run python export_onnx.py --checkpoint model.pth --onnx model.onnx

See export/hycoclip/README.md for details.

References

• HyCoCLIP
• MERU
• geoopt