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.
A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.
Decides
choice, score, noul, rank, classify, route
choice, noul, score
Architecture
clm
nanojev
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
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 nanojev?
clm is from Contrastive-LM and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice, score and noul questions. Only clm answers rank, classify and route. nanojev is the smaller model, at 600M parameters to 8.0B. clm is licensed apache-2.0; nanojev, mit.
Which is more accurate, clm or nanojev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or nanojev?
clm: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or nanojev locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull tianyu-codings/nanojev download the weights.
