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.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
julia
Fine-tuned from
qwen/qwen3-8b
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
73.2%
Calibration error
0.034
—
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 julia-1?
anyjev is from Nokia Applied Research and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. julia-1 is the smaller model, at 144M parameters to 8.0B.
Which is more accurate, anyjev or julia-1?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or julia-1?
anyjev: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or julia-1 locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull supersonic-labs/julia-1 download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
typed-decisions test set (400 cases, 2,000 questions)
