This model is a fine-tuned version of facebook/bart-base on an expanded version of the JFLEG dataset. You can find other grammar-synthesis models by searching for the grammar synthesis tag First, make sure you have the transformers package installed. You can install it using pip: This example demonstrates how to use the text-generation pipeline to correct the grammar in a given text. The corrector pipeline is initialized with the «pszemraj/bart-base-grammar-synthesis» model, which is designed for grammar correction. The corrector pipeline takes the raw text as input and returns the corrected text. Make sure to install the required dependencies and models before running the code. — robust grammar correction — the model has a license of cc-by-nc-sa-4.0 as it uses the JFLEG dataset + augments it for training The following hyperparameters were used during training: — learningrate: 0.0001 — trainbatchsize: 8 — evalbatchsize: 8 — seed: 42 — distributedtype: multi-GPU — gradientaccumulationsteps: 16 — totaltrainbatchsize: 128 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: cosine — lrschedulerwarmupratio: 0.02 — num_epochs: 3.0
Модальности:
Генерация текста
Задача: Генерация текста
Автор: pszemraj
Теги: onnx, bart, text2text-generation, grammar, spelling, punctuation, error-correction, grammar synthesis
Лайков: 2 | Загрузок: 579
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.