kev:9b
4 TagsUpdated 7.9B params8192 contextEnglishApache-2.0by Jared Palmer
Qwen3.5-9B base, 0.722 on typed decisions: the most accurate Kev. Needs a 24 GB GPU.
7.9b
ollaya run kev:9b --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": "kev:9b",
"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": "kev:9b",
"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: "kev:9b",
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
- graph43961763a149 · 14 MB
onnx · kev · 7.9B · fp32 - weights862bf7bba8a5 · 5.3 GB
huggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00001-of-00004.safetensors - weightsbace8e115e11 · 5.3 GB
huggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00002-of-00004.safetensors - weights63a021ac0011 · 5.4 GB
huggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00003-of-00004.safetensors - weights1a643bbed669 · 3.3 GB
huggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00004-of-00004.safetensors - weightsc02d0d1a7036 · 173 MB
huggingface.co/jaredpalmer/kev-9b/resolve/2629c06…/adapter_model.safetensors - weights5528f777437f · 8 MB
huggingface.co/jaredpalmer/kev-9b/resolve/2629c06…/head.pt - tokenizer06b9509352d2 · 20 MB
huggingface.co/jaredpalmer/kev-9b/resolve/2629c06…/tokenizer.json - decisionb63a05185c2a · 3 KB
{"engine": "onnx", "family": "kev", "encoder": "", "layout": "kev-pointer-v1", …} - calibration76c8fce9e9cb · 255 B
{"temperature": [2.297, 2.297, 2.297]} - licensec32fd125b858 · 10 KB
Kev by Jared Palmer (https://huggingface.co/jaredpalmer/kev-9b)
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.