An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
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.
Decides
choice, score, noul
choice, score, noul, rank, classify, route
Architecture
ajev
clm
Fine-tuned from
google/gemma-4-26b-a4b-it
qwen/qwen3-8b
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
49 ms
—
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 ajev and clm?
ajev is from Andy Zhang and clm from Contrastive-LM. Both have open weights you can download and run. Both answer choice, score and noul questions. Only clm answers rank, classify and route. clm is the smaller model, at 8.0B parameters to 26B.
Which is more accurate, ajev or clm?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, ajev or clm?
ajev: Free (open weights). clm: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run ajev or clm locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull contrastive-lm/clm download the weights.
