You can deploy this model and start earning money today!

polymathic-ai/
aion-large

Name: aion-large
Rating: 2.5 (53 reviews)

aion

safetensors

model_hub_mixin

pytorch_model_hub_mixin

any-to-any

MultimodalUniverse/legacysurvey

MultimodalUniverse/hsc

MultimodalUniverse/gaia

MultimodalUniverse/sdss

MultimodalUniverse/desi

2510.17960

mit

Views

No views yet

AION-1: Astronomical Omnimodal Network

AION-large is a 800M parameter large omnimodal model specifically designed for astronomical surveys. It integrates 39 distinct astronomical data types and enables adaptation to a wide range of astronomical tasks through multimodal masked modeling.

Model Details

Architecture: Encoder-Decoder Transformer (24 blocks each, 1024 dim, 16 heads)
Parameters: 300M
Training: Multimodal Masked Modeling (4M) on astronomical survey data
Modalities: 39 data types including imaging, spectra, catalogs, and photometry

Quick Start

python

from aion import AION

# Load the pretrained model
model = AION.from_pretrained('polymathic-ai/aion-large')

# Your astronomical analysis begins here!

Supported Data Types

AION-Base processes data from major astronomical surveys:

Imaging: Legacy Survey, HSC Wide
Spectra: SDSS, DESI
Catalog: Legacy Survey entries
Gaia: BP/RP spectra, parallax, coordinates, photometry
Photometry: Legacy Survey (g,r,i,z + WISE), HSC (g,r,i,z,y)
Shape: Ellipticity and morphological parameters

Installation

pip install polymathic-aion

Resources

License

MIT License - see https://github.com/PolymathicAI/AION/blob/main/LICENSE for details.

Built with ❤ for the astronomical community by https://polymathic-ai.org/