Transformers How to use lkwate/bert-nsp with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForNextSentencePrediction
tokenizer = AutoTokenizer.from_pretrained("lkwate/bert-nsp")
model = AutoModelForNextSentencePrediction.from_pretrained("lkwate/bert-nsp", device_map="auto") 
