A rank-16 LoRA on Qwen3.5-4B built for the JevBench setting. A document, a policy and a question go in; a calibrated distribution over the option letters comes out of one forward pass. Research and demo use only.
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
choice, score, noul, classify, route
Architecture
hopper
kev
Fine-tuned from
qwen/qwen3.5-4b
qwen/qwen3.5-4b-base
License
Research and demo use only (training data includes RACE, non-commercial); serving code Apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
68.5%
83.8%
Calibration error
0.102
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 hopper and kev?
hopper is from HopitAI and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only kev answers route. hopper is licensed other; kev, apache-2.0.
Which is more accurate, hopper or kev?
They report on different suites — hopper 68.5% on JevBench public hard tier (111 items, measured by the authors), 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, hopper or kev?
hopper: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run hopper or kev locally?
Yes, both: systemone pull hopit-ai/hopper and systemone pull jared-palmer/kev download the weights.
Evaluation suite
JevBench public hard tier (111 items, measured by the authors)
