YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

AzarielAI SAIR T1+T2 v0.2

Verified before packaging

  • Parameters: 1,215,329
  • Learned reducer domain: 12,114/12,114
  • Learned DLP encoder domain: 6,057/6,057
  • Learned decoder domain: 18,015/18,015
  • Random raw T1 smoke: 100/100 = 1.000
  • Random raw T2 smoke: 300/300 = 1.000
  • Perturbed-decoder control: 7/500 = 0.014

The exact finite-state checks are the important guarantee: every supported reducer transition, residue/DLP mapping, and reachable decoder latent sum was verified against the final trained weights.

Playground order

  1. T1 โ€” 100 cases (regression check)
  2. T2 โ€” 100 cases (target)
  3. Keep private until a ranked submission is intentionally chosen.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support