Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, classify, route
choice, rank, route
Architecture
laya
modernjev
Fine-tuned from
convai-innovations/laya
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
73.4%
Calibration error
—
—
Valid action rate
—
—
Median latency
116 ms
—
p95 latency
859 ms
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between laya-noulxp-cpu and modernjev-decide?
laya-noulxp-cpu is from Convai Innovations and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice and route questions. Only laya-noulxp-cpu answers score, noul and classify. Only modernjev-decide answers rank. modernjev-decide reads up to 4K tokens of state, against 512 tokens for laya-noulxp-cpu. modernjev-decide is the smaller model, at 150M parameters to 421M.
Which is more accurate, laya-noulxp-cpu or modernjev-decide?
Only modernjev-decide publishes an accuracy figure (73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)); laya-noulxp-cpu does not, so there is no comparison to make without your own test.
Which is cheaper, laya-noulxp-cpu or modernjev-decide?
laya-noulxp-cpu: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya-noulxp-cpu or modernjev-decide locally?
Yes, both: systemone pull convai-innovations/laya-noulxp-cpu and systemone pull maziyar-panahi/modernjev-decide download the weights.
Evaluation suite
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
