Fix model loading issue with older version of pytorch(<1.6) 78a2a6a
Pengcheng He commited on
How to use microsoft/deberta-base with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="microsoft/deberta-base") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("microsoft/deberta-base", device_map="auto")