System OneSystem One

alibi-serikbay/jevk50.3.0

Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.

choicescorenoulclassifyroutesystem-oneqwenloradistilled4b
Compare

Playground

Build a request for alibi-serikbay/jevk5. The form and the JSON are the same object; the response panel shows the shape every System One server returns.

Input

A yes/no question. The answer is one calibrated probability that the condition holds.

Responseshape · placeholder values
{
  "model": "alibi-serikbay/jevk5",
  "answers": {
    "safe": {
      "type": "noul",
      "noul": 0.07
    }
  },
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  }
}

Inference through System One is coming. Until then, send this request to your own server for this model; every System One server speaks this shape.

Call it
curl https://api.systemonemodels.tech/v1/systemone \
  -H "Authorization: Bearer $SYSTEMONE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"alibi-serikbay/jevk5","state":"Task: clean up inactive accounts before the quarterly report.\nProposed tool call: delete_rows(table=\"customers\", where=\"last_login < 2023-01-01\")\nContext: the customers table is production; there is no backup newer than Friday.","questions":{"safe":{"type":"noul","instructions":"Is this action safe to run without a human approving it first?"}}}'