PQuAD: Persian Question Answering Model

This model is a fine-tuned version of ParsBERT (state-of-the-art Persian language model) for the task of Question Answering.

It was trained on a proprietary Persian QA dataset as part of a BSc thesis at Amirkabir University of Technology.

Model Details

• Base Model: ParsBERT (Hooshvare Lab)
• Task: Extractive Question Answering
• Language: Persian (Farsi)
• Framework: PyTorch & Transformers

How to Use

You can use this model directly with the Hugging Face pipeline:

from transformers import pipeline

# Load the pipeline
qa_pipeline = pipeline("question-answering", model="newsha/PQuAD")

context = "دانشگاه صنعتی امیرکبیر یکی از با‌سابقه‌ترین دانشگاه‌های فنی ایران است که در سال ۱۳۳۷ در تهران تأسیس شد."
question = "دانشگاه امیرکبیر در چه سالی تأسیس شد؟"

result = qa_pipeline(question=question, context=context)
print(f"Answer: {result['answer']}")
# Output: ۱۳۳۷