m3hrdadfi/albert-fa-base-v2-clf-digimag

The task target is labeling texts in a supervised manner in both existing datasets DigiMag and Persian News . The model was trained based on Google's ALBERT BASE Version 2.0 over various writing styles from numerous subjects (e.g., scientific, novels, news) with more than 3.9M documents, 73M sentences, and 1.3B words, like the way we did for ParsBERT . This dataset includes seven different classes of texts . You can download the dataset from here . Please cite in publications as the following: AlberT-Persian: A Lite BERT for Self-supervised Learning of Language Representations for the Persian Language. [AL,