How to use sosuke/ease-roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="sosuke/ease-roberta-base")
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sosuke/ease-roberta-base") model = AutoModel.from_pretrained("sosuke/ease-roberta-base", device_map="auto")
