laya
Laya is a 421M-parameter non-LLM calibrated decision model: a ModernBERT-large encoder (28 layers, 1024 hidden, GeGLU, dual-theta RoPE, one global attention layer per three) with a 2-layer decision head that has an option-marker scorer and…
Community model. It is published as a tt-model bundle and is not in tt-inference-server's release spec. Tenstorrent has not reviewed the model or its bundle. Serve at your own risk.
tt-model bundles
| Bundle | Hardware | Served with | Context | Pushed | |
|---|---|---|---|---|---|
| tt-hous/laya | p150, BH 4xP150 | tt-dit-server | - | 2026-10-29 |
From tt-model search --catalog and each bundle's manifest (tt-model info). A bundle lists every hardware profile its manifest defines. Each bundle is published by its owner, and Tenstorrent has not reviewed it. Serve at your own risk.
Details
| Kind | Decision model (from the bundle card, which says it answers typed System One questions and generates no text) |
| Family | laya (from the start of the name) |
| License (bundle cards) | apache-2.0 |
| Listed by | tt-model bundle |