arabic quran nahj sahife

Introduction

The Arabic-Quran-Nahj-Sahife model is a specialized language model trained and fine-tuned on religious texts, including the Quran, Saheefa, and Nahj-al-Balaqa. It utilizes the BERT architecture for masked language modeling tasks in Arabic.

Architecture

This model is based on the BERT (Bidirectional Encoder Representations from Transformers) architecture, specifically fine-tuned on the Bert Base Arabic model. It supports fill-mask tasks, allowing users to predict missing words in a given text context.

Training

The model was fine-tuned using Masked Language Modeling (MLM) for 30 epochs. During training, words were completely masked every 5 epochs to improve the learning of embeddings and prevent overfitting. The training utilized datasets available from a specific repository, focusing on religious texts.

Guide: Running Locally

1. Clone the Repository: Ensure you have access to the model files and datasets required for local execution.
2. Install Dependencies: Make sure you have the Hugging Face Transformers library and PyTorch installed.
3. Load the Model: Utilize the Hugging Face's transformers library to load the model and tokenizer.
4. Run Inference: Use the model to perform fill-mask tasks locally.

To efficiently run the model, consider using cloud-based GPUs like those available on Google Cloud Platform, Amazon Web Services, or Azure for better performance.

License

This model is distributed under the GPL-2.0 license, permitting modification and distribution under the same terms.