Arabic Text-Target Classifier (LoRA) — t1_s10_allam7b_lora_prompt

3-class Arabic text classifier over (text, target) pairs, formulated as a prompted sequence-classification head on top of a LoRA-adapted instruction-tuned LLM. Access to the model weights requires manual approval from the repository owner.

Base model

humain-ai/ALLaM-7B-Instruct-preview

Labels

• LABEL_0
• LABEL_1
• LABEL_2

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
from peft import PeftModel
import torch

base_model_id = "humain-ai/ALLaM-7B-Instruct-preview"
adapter_id = "HassanB4/t1_s10_allam7b_lora_prompt"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base_model = AutoModelForSequenceClassification.from_pretrained(base_model_id, num_labels=3)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

text = "..."
target = "..."
prompt = f"{text} [SEP] {target}"
inputs = tokenizer(prompt, 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])