laya:multilingual-fp16
10 TagsUpdated 322M params1024 context100+ languagesApache-2.0by Convai Innovations
100+ languages, 1024-token context; up to ~2.2× faster on batched calls.
multilingual322m
ollaya run laya:multilingual-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": "laya:multilingual-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": "laya:multilingual-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: "laya:multilingual-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
- graphe44370875133 · 3 MB
onnx · mmBERT-base · 322M · fp32 - graph236fbdec33bd · 3 MB
onnx · mmBERT-base · 322M · fp16 - weights9d628fd971b7 · 644 MB
huggingface.co/convaiinnovations/laya/resolve/aa8c91c…/multilingual/model.safetensors - tokenizer609d8f4c067c · 34 MB
huggingface.co/convaiinnovations/laya/resolve/aa8c91c…/multilingual/tokenizer/tokenizer.json - decision5376e3133945 · 455 B
{"engine": "onnx", "family": "laya", "encoder": "jhu-clsp/mmBERT-base", "layout": "laya-markers-v1", …} - calibration316915b3e458 · 84 B
{"temperature": [1.0, 1.0, 1.0]} - licenseec56c3e69fab · 10 KB
Laya by Convai Innovations (https://huggingface.co/convaiinnovations/laya) - paramsa1d447ba672f · 21 B
precision fp16
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.