Transformers How to use microsoft/xdoc-base-funsd with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("token-classification", model="microsoft/xdoc-base-funsd") # Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("microsoft/xdoc-base-funsd")
model = AutoModelForTokenClassification.from_pretrained("microsoft/xdoc-base-funsd", device_map="auto") 
