This model is a fine-tuned version of distilgpt2 on a sample of amazonusreviews dataset. The sample was drawn from ‘Apparelv100’ subset. This model can auto generate review text for apparel products on providing product title, review rating (1-5) and review headline as an input prompt. The input prompt should be in the format producttitleproductratingreview_title. For example, Columbia Women’s Benton Springs Full-Zip Fleece Jacket5Awesome jacket!. You can find the complete code in my GitHub repository. This model is only intended to demonstrate the text generation capabilities of transformer-based models. Do not use it commercially or for any real-life purpose . The model is trained specifically on ‘Apparelv100’ dataset. So, using non-apparel product titles in the input prompt may yield inconsistent results. The following hyperparameters were used during training: — optimizer: {‘name’: ‘AdamWeightDecay’, ‘learningrate’: {‘classname’: ‘ExponentialDecay’, ‘config’: {‘initiallearningrate’: 0.0002, ‘decaysteps’: 1000, ‘decayrate’: 0.95, ‘staircase’: True, ‘name’: None}}, ‘decay’: 0.0, ‘beta1’: 0.9, ‘beta2’: 0.999, ‘epsilon’: 1e-07, ‘amsgrad’: False, ‘weightdecayrate’: 0.0} -…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: praveenseb
Теги: tf, gpt2, generated_from_keras_callback, endpoints_compatible
Лайков: 2 | Загрузок: 16
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.