decision:eos
2 TagsUpdated 0.75B params16384 contextEnglish, ChineseApache-2.0by vLLM Semantic Router
Decision 1.0 Eos, fully fine-tuned Qwen3.5-0.8B: 17.49 on Decision Index 0.2.
0.75b
ollaya run decision:eos --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": "decision:eos",
"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": "decision:eos",
"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: "decision:eos",
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
- graph7917445d40c7 · 8 MB
onnx · decision · 0.75B · fp32 - weights613f491da279 · 1.5 GB
huggingface.co/llm-semantic-router/Decision-1.0-Eos-0.8B/resolve/3c2d632…/backbone/model.safetensors - weights75f4ee8b512a · 4 MB
huggingface.co/llm-semantic-router/Decision-1.0-Eos-0.8B/resolve/3c2d632…/decision_head.safetensors - tokenizer06b9509352d2 · 20 MB
huggingface.co/llm-semantic-router/Decision-1.0-Eos-0.8B/resolve/3c2d632…/tokenizer.json - decision2a6f1ef91f03 · 3 KB
{"engine": "onnx", "family": "decision", "encoder": "", "layout": "decision-endpoint-v1", …} - calibration9cb229b1316a · 217 B
{"temperature": [1.039, 1.039, 1.039]} - license51ba79094bb8 · 10 KB
Decision 1.0 by the vLLM Semantic Router contributors (https://huggingface.co/llm-semantic-router)
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.