Search public pages, research tools, and SAVRN solutions.
Independent publisher
ajaxdavis
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text generation.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Self-contained x86-64 ELFs compiled by the Alpha compiler from one.alpha closure per system/target pairing. Each drives an NVIDIA GPU directly through the RM/UVM interface; there is no CUDA, Python or framework in the executable. They train, resume from a checkpoint and predict through the versioned text-artifact request protocol. manifest.json is the authority for the current sha256 of every file. Only the RTX 3090 pairings have been run on physical hardware.
Diakosmos (διάκοσμος, "the ordering of a world") is a byte-level harmonic recurrent language model, 99,823,934 parameters, written and trained from scratch in the Alpha language on a rented RTX 3070. It has no tokenizer and no attention matrix: each byte enters as a fixed constellation of phasors (the wiretable), and each of 14 blocks blends a decaying harmonic recurrence over the past with a planar rotation between seven wire groups. Its design is harmonic-gpt's leading model. The tensors carry harmonic-gpt's parameter names; wiretable is the fixed byte encoding (256 x 1330). updates of 64 windows, 24.5 GPU hours and 5.29 kWh on one RTX 3070. Held-out OpenWebText: 1.4194 bits per byte…