How to use Billwzl/20split_dataset_version4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Billwzl/20split_dataset_version4")
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Billwzl/20split_dataset_version4") model = AutoModelForMaskedLM.from_pretrained("Billwzl/20split_dataset_version4", device_map="auto")
What is a pickle import?
How to fix it?
