YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
This model is used to determine if a domain name is malicious or not. It should be used only as a suggestion as it does have some false positives, especialy on domains from other countries.
tags: - autotrain - text-classification language: - en widget: - text: "I love AutoTrain 🤗" datasets: - Cubicz/autotrain-data-domain-filer-2 co2_eq_emissions: emissions: 2.854698438703003
Model Trained Using AutoTrain
- Problem type: Binary Classification
- Model ID: 3436193686
- CO2 Emissions (in grams): 2.8547
Validation Metrics
- Loss: 0.124
- Accuracy: 0.967
- Precision: 0.963
- Recall: 0.963
- AUC: 0.991
- F1: 0.963
Usage
You can use cURL to access this model:
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/Cubicz/autotrain-domain-filer-2-3436193686
Or Python API:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("Cubicz/autotrain-domain-filer-2-3436193686", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("Cubicz/autotrain-domain-filer-2-3436193686", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.