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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
mira
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%
74.5%
Calibration error
0.034
0.025
Valid action rate
—
100.0%
Median latency
—
30 ms
p95 latency
—
43 ms
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
s1-decision-bench
Latest version
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 mira?
anyjev is from Nokia and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, anyjev or mira?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, mira 74.5% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or mira?
anyjev: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or mira locally?
Yes, both: systemone pull nokia/anyjev and systemone pull sagea/mira download the weights.
