decision2:sol
6 TagsUpdated 1.88B params16384 contextEnglishApache-2.0by vLLM Semantic Router
Qwen3.5-2B: 0.554 on typed decisions.
1.88b
ollaya run decision2:sol --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:sol",
"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:sol",
"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:sol",
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
- graphdb840091efa5 · 9 MB
onnx · decision2 · 1.88B · fp32 - weights2213a6559dd4 · 3.0 GB
huggingface.co/vllm-sr/Decision-2.0-Sol-2B/resolve/df30237…/backbone/model-00001-of-00002.safetensors - weightsff7a564a5aa7 · 1.8 GB
huggingface.co/vllm-sr/Decision-2.0-Sol-2B/resolve/df30237…/backbone/model-00002-of-00002.safetensors - weights0999f3c4bec4 · 8 MB
huggingface.co/vllm-sr/Decision-2.0-Sol-2B/resolve/df30237…/decision_head.safetensors - tokenizer06b9509352d2 · 20 MB
huggingface.co/vllm-sr/Decision-2.0-Sol-2B/resolve/df30237…/tokenizer.json - decisionf5fbd1b971d1 · 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.