Transformers How to use KoichiYasuoka/chinese-roberta-base-upos with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("token-classification", model="KoichiYasuoka/chinese-roberta-base-upos") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("KoichiYasuoka/chinese-roberta-base-upos")
model = AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/chinese-roberta-base-upos", device_map="auto") 
