This model is a fine-tuned version of Mistral, specifically optimized for generating quizzes, exams, and educational questions based on given prompts or contexts.

Model Description

Task: Text Generation / Question Generation (توليد أسئلة واختبارات)
Languages Supported: Arabic and English
Intended Use: Educational applications, teachers' assistance, and automatic quiz generation.

How to use (كيفية الاستخدام برمجياً)

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "oewis16/mistral-exam-generator"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    device_map="auto"
)

prompt = "اكتب سؤال اختيار من متعدد عن الذكاء الاصطناعي مع الإجابات:"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=150)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))