Fine-tuned model of Arabic poetry dataset based on aragpt2-medium. Both the GPT2-small-arabic (trained on Arabic Wikipedia) and this model have several limitations in terms of coverage and training performance. Use them as demonstrations or proof of concepts but not as production code. This pretrained model used poems from several eras with a total of around 1.4M lines (1.25M used for training). The dataset was trained (fine-tuned) based on the aragpt2-medium transformer model. Training was done using HF Trainer using free GPU on Kaggle. Final perplexity reached was 52, evalaccuracy = 0.3704, evalloss = 3.9513
Модальности:
Генерация текста
Задача: Генерация текста
Автор: akhooli
Теги: gpt2, ar, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 108
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
