How to use grace-pro/no-deletion-3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="grace-pro/no-deletion-3")
# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("grace-pro/no-deletion-3") model = AutoModelForTokenClassification.from_pretrained("grace-pro/no-deletion-3", device_map="auto")
What is a pickle import?
How to fix it?
