A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
kev
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
83.8%
Calibration error
0.034
0.042
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 anyjev and kev?
anyjev is from Nokia Applied Research and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. kev is the smaller model, at 4.0B parameters to 8.0B.
Which is more accurate, anyjev or kev?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, kev 83.8% on transfer-v4 (locked, out of domain) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or kev?
anyjev: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or kev locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull jared-palmer/kev download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
