decision2:nox
6 TagsUpdated 4.21B params16384 contextEnglishApache-2.0by vLLM Semantic Router
Qwen3.5-4B-Base: 0.680 on typed decisions; 251 ms for five questions on an RTX 5090.
4.21b
ollaya run decision2:nox --preset triage "I was charged twice for my subscription this month and want a refund."curl http://localhost:11435/api/decide \
-H "Content-Type: application/json" \
-d '{
"model": "decision2:nox",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
}'# Already using a TypeSafe SDK? Set TYPESAFE_BASE_URL=http://localhost:11435 instead.
import requests
response = requests.post(
"http://localhost:11435/api/decide",
json={
"model": "decision2:nox",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
},
)
answers = response.json()["answers"]
print(answers["department"]["choice"], answers["refund"]["noul"])const response = await fetch("http://localhost:11435/api/decide", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model: "decision2:nox",
state: "I was charged twice for my subscription this month and want a refund.",
questions: {
department: {
type: "choice",
instructions: "Which team should handle this?",
criteria: {
billing: "Payments, invoices and refunds",
technical: "Bugs, errors and outages",
account: "Login, profile and settings"
}
},
refund: {
type: "noul",
instructions: "Is the customer asking for a refund?"
}
}
}),
});
const { answers } = await response.json();
console.log(answers.department.choice, answers.refund.noul);Details
- graph1298f0b5d137 · 12 MB
onnx · decision2 · 4.21B · fp32 - weights43d4d5f982e1 · 3.3 GB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/backbone/model-00001-of-00005.safetensors - weights244d869ac781 · 2.0 GB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/backbone/model-00002-of-00005.safetensors - weights8add5d59b305 · 2.0 GB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/backbone/model-00003-of-00005.safetensors - weightse542793a3660 · 2.0 GB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/backbone/model-00004-of-00005.safetensors - weightsf86e1c897e54 · 488 MB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/backbone/model-00005-of-00005.safetensors - weights5ebd2939cc82 · 11 MB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/decision_head.safetensors - tokenizer06b9509352d2 · 20 MB
huggingface.co/vllm-sr/Decision-2.0-Nox-4B/resolve/ae269ec…/tokenizer.json - decision6fa1c431ae2d · 5 KB
{"engine": "onnx", "family": "decision2", "encoder": "", "layout": "decision2-endpoint-v1", …} - calibrationbf756c46be45 · 187 B
{"temperature": [1.0, 1.0, 1.0]} - license1314ad54d94f · 10 KB
Decision 2.0 by the vLLM Semantic Router contributors (https://huggingface.co/vllm-sr)
Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.