Arabic Text-Target Classifier — t1_s9_mbert_text_target

3-class Arabic text classifier over (text, target) pairs. Access to the model weights requires manual approval from the repository owner.

Base model

google-bert/bert-base-multilingual-cased

Labels

• LABEL_0
• LABEL_1
• LABEL_2

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("HassanB4/t1_s9_mbert_text_target")
model = AutoModelForSequenceClassification.from_pretrained("HassanB4/t1_s9_mbert_text_target")
model.eval()

text = "..."
target = "..."
inputs = tokenizer(text, target, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    logits = model(**inputs).logits

predicted_label = int(torch.argmax(logits, dim=-1)[0])