How to use pinecone/bert-mrpc-cross-encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="pinecone/bert-mrpc-cross-encoder")
# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("pinecone/bert-mrpc-cross-encoder") model = AutoModelForSequenceClassification.from_pretrained("pinecone/bert-mrpc-cross-encoder")
What is a pickle import?
