perfecXion/intentguard-legal

IntentGuard — Legal Services (legal)

Vertical intent classifier for LLM chatbot guardrails. Classifies user messages as allow, deny, or abstain based on whether they fall within the legal domain.

Model Details

• Architecture: DeBERTa-v3-xsmall fine-tuned for 3-way classification
• Format: ONNX (INT8 quantized)
• Version: 1.0
• Vertical: legal (Legal Services)
• Publisher: perfecXion.ai

Performance

Metric	Value
Overall Accuracy	N/A
Adversarial Accuracy	N/A
p99 Latency (CPU)	N/A
Model Size	2.5MB

Usage

Python (ONNX Runtime)

import onnxruntime as ort
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("perfecXion/intentguard-legal")
session = ort.InferenceSession("model.onnx")

inputs = tokenizer("What are mortgage rates?", return_tensors="np")
logits = session.run(None, dict(inputs))[0]

Docker

docker pull ghcr.io/perfecxion/intentguard:legal-1.0
docker run -p 8080:8080 ghcr.io/perfecxion/intentguard:legal-1.0

curl -X POST http://localhost:8080/v1/classify \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "What are mortgage rates?"}]}'

pip

pip install intentguard

Core Topics

contracts, litigation, employment law, intellectual property, criminal law, family law, real estate law, immigration, corporate law, compliance, privacy law, civil rights, estate planning, bankruptcy

License

Apache 2.0