This is a fine-tuned version of Multilingual Bart trained (610M) on English in particular on the public dataset FCE for Grammatical Error Correction.

To initialize the model:

from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
model = MBartForConditionalGeneration.from_pretrained("MRNH/mbart-english-grammar-corrector")

Use the tokenizer:

tokenizer = MBart50TokenizerFast.from_pretrained("MRNH/mbart-english-grammar-corrector", src_lang="en_XX", tgt_lang="en_XX")

input = tokenizer("I was here yesterday to studying",
                  text_target="I was here yesterday to study", return_tensors='pt')

To generate text using the model:

output = model.generate(input["input_ids"],attention_mask=input["attention_mask"],
                        forced_bos_token_id=tokenizer_it.lang_code_to_id["en_XX"])

Training of the model is performed using the following loss computation based on the hidden state output h:

h.logits, h.loss = model(input_ids=input["input_ids"],
                                              attention_mask=input["attention_mask"],
                                              labels=input["labels"])
Downloads last month
50,430
Inference API