d3:latest
6 TagsUpdated 4B params8192 contextEnglishApache-2.0by vLLM Semantic Router
Same as d3:mini.
4b
ollaya run d3 --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": "d3",
"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": "d3",
"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: "d3",
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
- graph1ba29558a7d5 · 12 MB
onnx · d3 · 4B · fp32 - weights60621cb8c3f9 · 5.0 GB
huggingface.co/vllm-sr/d3-mini/resolve/bd0090d…/model-00001-of-00002.safetensors - weights6189569fbe92 · 4.1 GB
huggingface.co/vllm-sr/d3-mini/resolve/bd0090d…/model-00002-of-00002.safetensors - weightsd570665c1da7 · 3 MB
huggingface.co/vllm-sr/d3-mini/resolve/bd0090d…/readout.safetensors - tokenizer06b9509352d2 · 20 MB
huggingface.co/bespokelabs/Bespoke-Nimble-9B-v2/resolve/4b8c04d…/tokenizer.json - decision962d8401c26f · 5 KB
{"engine": "onnx", "family": "d3", "encoder": "", "layout": "d3-code-readout-v1", …} - calibration0f89e51fde90 · 133 B
{"temperature": [1.0, 1.0, 1.0]} - license3d7ec11263ac · 10 KB
Decision 3.0 (d3) 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.