Transformers How to use autoevaluate/translation-not-evaluated with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("autoevaluate/translation-not-evaluated")
model = AutoModelForSeq2SeqLM.from_pretrained("autoevaluate/translation-not-evaluated", device_map="auto") 
