Xlm Roberta Base Finetuned Urdu

🚀 XLM-RoBERTa-Urdu-Classification

This model, based on xlm-roberta-base, is trained on Urdu sentiment data-set and can perform binary sentiment classification on any given Urdu sentence. It has been fine - tuned for better results within a manageable time frame.

🚀 Quick Start

This xlm-roberta-base text classification model, trained on Urdu sentiment data-set, is capable of performing binary sentiment classification on any given Urdu sentence. The model has undergone fine - tuning to achieve better results in reasonable time frames.

✨ Features

• Cross - lingual Encoder: XLM - RoBERTa is a scaled cross - lingual sentence encoder trained on 2.5T of data across 100 languages filtered from Common Crawl.
• State - of - the - art Results: It achieves state - of - the - art results on multiple cross - lingual benchmarks.
• Fine - tuned for Urdu: Specifically fine - tuned for binary sentiment classification on Urdu sentences.

📚 Documentation

Model description

XLM - RoBERTa is a scaled cross - lingual sentence encoder. It is trained on 2.5T of data across 100 languages data filtered from Common Crawl. XLM - R achieves state - of - the - arts results on multiple cross - lingual benchmarks.

The XLM - RoBERTa model was proposed in Unsupervised Cross - lingual Representation Learning at Scale by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov.

It is based on Facebook’s RoBERTa model released in 2019. It is a large multi - lingual language model, trained on 2.5TB of filtered CommonCrawl data.

💻 Usage Examples

Basic Usage

You can import this model directly from the transformers library:

>>> from transformers import AutoTokenizer, AutoModelForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("Aimlab/xlm-roberta-base-finetuned-urdu")
>>> model = AutoModelForSequenceClassification.from_pretrained("Aimlab/xlm-roberta-base-finetuned-urdu", id2label = {0: 'negative', 1: 'positive'})

Advanced Usage

Here is how to use this model to get the label of a given text:

>>> from transformers import TextClassificationPipeline
>>> text = "وہ ایک برا شخص ہے"
>>> pipe = TextClassificationPipeline(model = model, tokenizer = tokenizer, top_k = 2, device = 0)
>>> pipe(text)

[{'label': 'negative', 'score': 0.9987003803253174},
 {'label': 'positive', 'score': 0.001299630501307547}]

📄 License

This project is licensed under the AFL - 3.0 license.