pplx-decider:flash-fp16
3 TagsUpdated 4B params8192 context100+ languagesApache-2.0by Perplexity AI
pplx-decider-flash v1.2: Qwen3.5-4B post-trained by Perplexity (distilled from its 27B decision models), with a 255-code readout. Every question of a request shares one sequence, read at a marker after each question; the full-attention layers see the whole request. Up to 255 options and levels, 8,192 tokens per sequence. Needs about 9 GB of memory. This tag computes in fp16 on NVIDIA GPUs: faster than pplx-decider:flash, with at least 99.5 % of its decisions the same. On a CPU it runs, slowly; use pplx-decider:flash there.
ollaya run pplx-decider:flash-fp16 --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": "pplx-decider:flash-fp16",
"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": "pplx-decider:flash-fp16",
"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: "pplx-decider:flash-fp16",
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
- graph53b1e1de9a91 · 12 MB
onnx · pplx · 4B · fp16 - weights1c1a0c1ab331 · 5.0 GB
huggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/model-00001-of-00002.safetensors - weights21ba8301660e · 4.1 GB
huggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/model-00002-of-00002.safetensors - weights675157817102 · 1 MB
huggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/readout.safetensors - tokenizer6f32ce20dc35 · 20 MB
huggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/tokenizer.json - decisiondac0a11b7ea1 · 6 KB
{"engine": "onnx", "family": "pplx", "encoder": "", "layout": "pplx-joint-v1", …} - calibration4e7a506638b7 · 223 B
{"temperature": [1.554, 1.554, 1.554]} - license74080187543c · 11 KB
pplx-decider-flash-v1.2 by Perplexity AI (https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2)
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.