parsbert-persian-QA / README.md
mansoorhamidzadeh's picture
Update README.md
7e49fa4 verified
|
raw
history blame
2.02 kB
metadata
license: apache-2.0
language:
  - fa
pipeline_tag: question-answering
tags:
  - persain
  - persian_qa
  - parsbert
metrics:
  - accuracy
datasets:
  - SajjadAyoubi/persian_qa

Model Card for Model ID

ParsBERT for Persian Question Answering

Model Description

this is a fine-tuned version of the ParsBERT model, specifically adapted for the task of question answering in Persian. ParsBERT is a BERT-based model pre-trained on a large Persian text corpus. This model has been fine-tuned on a Persian QA dataset to provide accurate and contextually relevant answers to questions posed in Persian.

Model Architecture

  • Base Model: ParsBERT
  • Task: Question Answering
  • Language: Persian
  • Number of Parameters: 110M

Intended Use

This model is intended for use in applications requiring natural language understanding and question answering in Persian, such as:

  • Persian language chatbots
  • Persian information retrieval systems
  • Educational tools for Persian language learners

Dataset

The model was fine-tuned on a Persian QA dataset. The dataset consists of question-answer pairs extracted from various Persian text sources, ensuring a diverse range of topics and contexts.

Usage

To use this model for question answering in Persian, you can load it using the Hugging Face Transformers library. Here’s a quick example:

from transformers import AutoTokenizer, AutoModelForQuestionAnswering, pipeline

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mansoorhamidzadeh/parsbert-persian-QA")
model = AutoModelForQuestionAnswering.from_pretrained("mansoorhamidzadeh/parsbert-persian-QA")

# Create a QA pipeline
qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)

# Example usage
context = "متن زمینه که شامل اطلاعات مرتبط با سوال شما است."
question = "سوال شما چیست؟"
result = qa_pipeline(question=question, context=context)

print(f"Answer: {result['answer']}")