sura:0.8b
3 TagsUpdated 0.8B params8192 contextEnglishApache-2.0by Ollaya
Qwen3.5-0.8B: 0.560 on typed decisions, zero-shot; 60 ms for five questions on an RTX 5090.
0.8b
ollaya run sura:0.8b --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": "sura:0.8b",
"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": "sura:0.8b",
"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: "sura:0.8b",
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
- graph38b6a8bf9074 · 8 MB
onnx · pplx · 0.8B · fp32 - weightsf5bd00594d50 · 1.7 GB
huggingface.co/ollaya-dev/sura-0.8b/resolve/9e991fa…/model.safetensors - weightsd51e8cdec401 · 522 KB
huggingface.co/ollaya-dev/sura-0.8b/resolve/9e991fa…/readout.safetensors - tokenizer6f32ce20dc35 · 20 MB
huggingface.co/ollaya-dev/sura-0.8b/resolve/9e991fa…/tokenizer.json - decisioneef33f2fe2ea · 6 KB
{"engine": "onnx", "family": "pplx", "encoder": "", "layout": "pplx-joint-v1", …} - calibration4480c0e1f156 · 181 B
{"temperature": [0.93, 0.93, 0.93]} - licensee883397b3998 · 11 KB
Sura by Ollaya (https://huggingface.co/ollaya-dev)
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.