How to use negentropi/belgin-privacy-filter with PEFT:
from peft import PeftModel from transformers import AutoModelForTokenClassification base_model = AutoModelForTokenClassification.from_pretrained("openai/privacy-filter") model = PeftModel.from_pretrained(base_model, "negentropi/belgin-privacy-filter")
How to use negentropi/belgin-privacy-filter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="negentropi/belgin-privacy-filter")
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("negentropi/belgin-privacy-filter", device_map="auto")
