Instructions to use teimurjan/legal-clause-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teimurjan/legal-clause-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="teimurjan/legal-clause-classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("teimurjan/legal-clause-classifier") model = AutoModelForSequenceClassification.from_pretrained("teimurjan/legal-clause-classifier") - Transformers.js
How to use teimurjan/legal-clause-classifier with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-classification', 'teimurjan/legal-clause-classifier'); - Notebooks
- Google Colab
- Kaggle
Legal Clause Classifier (ONNX)
Multi-label classifier for legal document clauses. Identifies clause types and associated risk levels.
Model Details
- Architecture: BERT-based sequence classification
- Format: ONNX (optimized for browser inference)
- Labels: 41 legal clause categories
- Risk Levels: high, medium, low
Usage with transformers.js
import { pipeline } from '@huggingface/transformers';
const classifier = await pipeline(
'text-classification',
'teimurjan/legal-clause-classifier',
{ device: 'wasm' }
);
const result = await classifier(
'The Company shall indemnify and hold harmless the Contractor from any claims.'
);
console.log(result);
Labels
The model classifies text into 41 legal clause categories including:
- Indemnification
- Limitation of Liability
- Termination
- Confidentiality
- Governing Law
- And 36 more...
Each label includes a risk assessment (high/medium/low) in label_config.json.
License
MIT
- Downloads last month
- 3