How to use Billwzl/20split_dataset with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Billwzl/20split_dataset")
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Billwzl/20split_dataset") model = AutoModelForMaskedLM.from_pretrained("Billwzl/20split_dataset", device_map="auto")
What is a pickle import?
How to fix it?
