How to use mjwong/multilingual-e5-large-instruct-xnli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="mjwong/multilingual-e5-large-instruct-xnli")
# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mjwong/multilingual-e5-large-instruct-xnli") model = AutoModelForSequenceClassification.from_pretrained("mjwong/multilingual-e5-large-instruct-xnli")
What is a pickle import?
How to fix it?
