Modelpublic

elisabeth-pl-pl/Finetuned-RADAR-binary-classification

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes7downloads

Model Card

Finetuned RADAR — AI Text Detector

Fine-tuned version of TrustSafeAI/RADAR-Vicuna-7B (RoBERTa classifier) via LoRA for binary AI-generated text detection.

Usage

python

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_id = "elisabeth-pl-pl/Finetuned-RADAR-binary-classification"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)

text = "Your text here"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
with torch.no_grad():
    logits = model(**inputs).logits
pred = logits.argmax(-1).item()
print("machine" if pred == 0 else "human")

Labels

—0 — machine-generated
—1 — human-written