nli:modernbert-large
3 TagsUpdated 396M params512 contextEnglishMITby Moritz Laurer
ModernBERT-large, Apache-2.0. Faster, slightly less accurate (0.515).
396m
ollaya run nli:modernbert-large --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": "nli:modernbert-large",
"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": "nli:modernbert-large",
"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: "nli:modernbert-large",
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
- graphda223fdbe719 · 4 MB
onnx · ModernBERT-large-zeroshot-v2.0 · 396M · fp32 - weights9e88e3ba0721 · 792 MB
huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0/resolve/a51e07b…/model.safetensors - tokenizer6c8aaa9a5420 · 4 MB
huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0/resolve/a51e07b…/tokenizer.json - decisione47095bd7afa · 1 KB
{"engine": "onnx", "family": "nli", "encoder": "MoritzLaurer/ModernBERT-large-zeroshot-v2.0", "layout": "nli-pairs-v1", …} - calibration316915b3e458 · 84 B
{"temperature": [1.0, 1.0, 1.0]} - license445805446407 · 10 KB
ModernBERT-large zero-shot v2.0 by Moritz Laurer (https://huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0)
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.