Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
Unofficial NoulXP package of Convai Innovations' Laya typed-decisions (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
laya
Fine-tuned from
qwen/qwen3-8b
convai-innovations/laya
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
126 ms
p95 latency
—
2185 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 clm and laya-typed-decisions-noulxp?
clm is from Contrastive-LM and laya-typed-decisions-noulxp from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. laya-typed-decisions-noulxp is the smaller model, at 421M parameters to 8.0B.
Which is more accurate, clm or laya-typed-decisions-noulxp?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or laya-typed-decisions-noulxp?
clm: Free (open weights). laya-typed-decisions-noulxp: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or laya-typed-decisions-noulxp locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull convai-innovations/laya-typed-decisions-noulxp 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
