from transformers import AutoModelForSequenceClassification, AutoTokenizer, TextClassificationPipeline

model_path = "ZiruiXiong/bert-base-finetuned-toxic-comment-classification"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)

pipeline = TextClassificationPipeline(model=model, tokenizer=tokenizer)
print(pipeline('You are also a liar since I hardly spoke with you.'))

Evaluation results

The model achieves 0.95 AUC in a 1500 rows held-out test set.