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.
An embedding model turned decision model. Qwen3-Embedding-4B with a merged LoRA, driven by the open JevEmbed toolkit, which scores Choice, Score and Noul questions from embedding similarity and returns a distribution without generating text.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify
Architecture
clm
jevembed
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3-embedding-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
85.9%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
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 jevembed?
clm is from Contrastive-LM and jevembed from HIT-TMG (Lychee Team). Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only clm answers rank and route. jevembed is the smaller model, at 4.0B parameters to 8.0B.
Which is more accurate, clm or jevembed?
Only jevembed publishes an accuracy figure (85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or jevembed?
clm: Free (open weights). jevembed: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or jevembed locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull hit-tmg/jevembed download the weights.
—
Evaluation suite
—
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
