Transformers How to use PrimeQA/squad-v1-roberta-large with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, RobertaModelForDownstreamTasks
tokenizer = AutoTokenizer.from_pretrained("PrimeQA/squad-v1-roberta-large")
model = RobertaModelForDownstreamTasks.from_pretrained("PrimeQA/squad-v1-roberta-large", device_map="auto") 
