laya
The most-liked open-weight decision model of the post-Jev wave, a 421M ModernBERT-large encoder. The base release of a three-model family.
Community card
What it is
Laya is a 421M-parameter encoder on ModernBERT-large, and at 786 likes it is the most-liked
model in this directory by a wide margin. It anchors a family: laya-typed-decisions is the
variant tuned on the community benchmark set, and laya-multilingual swaps the base for mmBERT.
Attention is not measurement
786 likes is a signal about how much people want an open answer to Jev, not about how well this model decides. Every model in this directory was published inside five days of Jev’s release, which is not enough time for anyone’s numbers to have been checked by a third party. That is the gap this site exists to close.
Treat the base laya checkpoint as the general-purpose starting point and
laya-typed-decisions as the one to compare against published
figures, since that is the variant whose card carries them.
Status
Not yet benchmarked by us. It is an encoder in the few-hundred-megabyte range, so evaluating it is minutes of CPU time rather than hours, and it runs in the first open-weight batch.
Sources
Every fact on this page traces to one of these, checked on the date shown. Download and like counts move; the rest of it should not.
- Hugging Face · convaiinnovations/layachecked 20 September 2026
Page last verified 20 September 2026.
A public number is a shortlist, not a decision
The only benchmark that settles which model you ship is one built from your own historical decisions. We freeze that test set, run the candidates against it, and hand back the threshold your error budget supports.