metadata
language:
- it
pipeline_tag: translation
To initialize the model:
```python
from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50", output_hidden_states=True)
```
To generate text using the model:
```python
tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50", src_lang="it_IT", tgt_lang="it_IT")
input_ids = tokenizer.encode("Input text", return_tensors="pt")
output = model.generate(input_ids)
```