Transformers How to use Intel/nq_fid_lfqa_early_exit with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, FiDT5
tokenizer = AutoTokenizer.from_pretrained("Intel/nq_fid_lfqa_early_exit")
model = FiDT5.from_pretrained("Intel/nq_fid_lfqa_early_exit", device_map="auto") 
