from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("trieutm/mbart-large-50-many-to-many-mmt-finetuned-vi-to-en")
model = AutoModelForSeq2SeqLM.from_pretrained("trieutm/mbart-large-50-many-to-many-mmt-finetuned-vi-to-en")

For inference

Use a pipeline as a high-level helper

python

from transformers import pipeline

pipe = pipeline("translation", model="trieutm/mbart-large-50-many-to-many-mmt-finetuned-vi-to-en")