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.
The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
decider
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-2b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
80.2%
Calibration error
0.034
0.038
Valid action rate
—
—
Median latency
—
3.2 ms
p95 latency
—
—
Evaluation suite
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 decider?
anyjev is from Nokia Applied Research and decider from Mapika. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 2.0B parameters to 8.0B.
Which is more accurate, anyjev or decider?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, decider 80.2% on Decider 67-task regression set — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or decider?
anyjev: Free (open weights). decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or decider locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull mapika/decider download the weights.
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
