How to use deepset/gelectra-base-generator with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="deepset/gelectra-base-generator")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("deepset/gelectra-base-generator") model = AutoModelForMaskedLM.from_pretrained("deepset/gelectra-base-generator", device_map="auto")
