Purge duplicate "decoder.weight", rely on tied weights instead 9459040
Tom Aarsen commited on
How to use stefan-it/ModernBERT-large-tokenizer-fix with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="stefan-it/ModernBERT-large-tokenizer-fix") # Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("stefan-it/ModernBERT-large-tokenizer-fix")
model = AutoModelForMaskedLM.from_pretrained("stefan-it/ModernBERT-large-tokenizer-fix", device_map="auto")