Open source

What is in the box

Apache-2.0, weights on Hugging Face, a Zenodo DOI — and a clear list of what stays internal.

The architecture, the C99 engine, the ternary export format and a 944,000-parameter TinyStories checkpoint are public under Apache-2.0. This page says exactly what is in the box and what is not, because "open source" on an AI project can mean anything from a full training path to a weights download with a licence attached.

What is public

ArtifactWhereWhat it contains
Sourcegithub.com/TilelliLab/atome-lmThe three-pathway architecture, the zero-heap C99 inference engine, the ATOME01 packing format, the parity tests, the RAM measurement script.
Weightshuggingface.co/TilelliLab/atome-lmThe trained checkpoints, including the 944,000-parameter TinyStories model.
Citation10.5281/zenodo.20518644A citable DOI for the release.
LicenceApache-2.0Commercial use permitted, patent grant included, attribution required.

What is not public, and why

Reproducing the published numbers

Every figure on this site that concerns the public kit comes from a script in it:

The full reading of the perplexity results, including the ones where the architecture loses, is in HONEST_RESULTS.md in the repository.

Using it in a product

Apache-2.0 means you can ship it commercially without asking. What people generally want help with is not the licence but the bring-up: getting a model of the right size onto a specific part, secure boot and signed model loading, per-platform hardening, and the evidence pack a certification body will ask for. That is what the services page is about.

Citing it

If Atome LM is useful in academic work, cite the Zenodo DOI 10.5281/zenodo.20518644. If you benchmark it and it loses, publish that too — we do, on the limitations page, and a negative result about a small model is worth more to the field than another positive one about a large one.