How to use bztest/xlm-roberta-base-finetuned-panx-de with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="bztest/xlm-roberta-base-finetuned-panx-de")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("bztest/xlm-roberta-base-finetuned-panx-de") model = AutoModelForTokenClassification.from_pretrained("bztest/xlm-roberta-base-finetuned-panx-de", device_map="auto")
What is a pickle import?
How to fix it?
